Merge branch 'develop'

[MIG] Migrated buy_and_hodl and buy_low_sell_high to version 0.3 to work with Poloniex exchange

README.rst

@@ -1 +1,3 @@
-All the documentation for `Catalyst <https://github.com/enigmampc/catalyst>`_ can be found in the `catalyst-docs wiki <https://github.com/enigmampc/catalyst-docs/wiki>`_.
+All the documentation for `Catalyst <https://github.com/enigmampc/catalyst>`_
+can be found in the 
+`documentation website <https://enigmampc.github.io/catalyst>`_.

catalyst/__main__.py

@@ -8,6 +8,8 @@ import pandas as pd
 from six import text_type
 
 from catalyst.data import bundles as bundles_module
+from catalyst.exchange.exchange_bundle import ExchangeBundle
+from catalyst.exchange.factory import get_exchange
 from catalyst.utils.cli import Date, Timestamp
 from catalyst.utils.run_algo import _run, load_extensions
 
@@ -36,8 +38,9 @@ except NameError:
     '--default-extension/--no-default-extension',
     is_flag=True,
     default=True,
-    help="Don't load the default catalyst extension.py file in $ZIPLINE_HOME.",
+    help="Don't load the default catalyst extension.py file in $CATALYST_HOME.",
 )
+@click.version_option()
 def main(extension, strict_extensions, default_extension):
     """Top level catalyst entry point.
     """
@@ -126,7 +129,7 @@ def ipython_only(option):
 )
 @click.option(
     '--data-frequency',
-    type=click.Choice({'daily', '5-minute', 'minute'}),
+    type=click.Choice({'daily', 'minute'}),
     default='daily',
     show_default=True,
     help='The data frequency of the simulation.',
@@ -187,17 +190,11 @@ def ipython_only(option):
     default=None,
     help='Should the algorithm methods be resolved in the local namespace.'
 ))
-@click.option(
-    '--live/--no-live',
-    is_flag=True,
-    default=False,
-    help='Enable live trading.',
-)
 @click.option(
     '-x',
     '--exchange-name',
-    type=click.Choice({'bitfinex', 'bittrex'}),
-    help='The name of the targeted exchange (supported: bitfinex, bittrex).',
+    type=click.Choice({'bitfinex', 'bittrex', 'poloniex'}),
+    help='The name of the targeted exchange (supported: bitfinex, bittrex, poloniex).',
 )
 @click.option(
     '-n',
@@ -210,12 +207,6 @@ def ipython_only(option):
     help='The base currency used to calculate statistics '
          '(e.g. usd, btc, eth).',
 )
-@click.option(
-    '--live-graph/--no-live-graph',
-    is_flag=True,
-    default=False,
-    help='Display live graph.',
-)
 @click.pass_context
 def run(ctx,
         algofile,
@@ -230,44 +221,34 @@ def run(ctx,
         output,
         print_algo,
         local_namespace,
-        live,
         exchange_name,
         algo_namespace,
-        base_currency,
-        live_graph):
+        base_currency):
     """Run a backtest for the given algorithm.
     """
 
-    if live:
-        if exchange_name is None:
-            ctx.fail("must specify an exchange name '-x' in live execution "
-                     "mode '--live'")
-        if algo_namespace is None:
-            ctx.fail("must specify an algorithm name '-n' in live execution "
-                     "mode '--live'")
-        if base_currency is None:
-            ctx.fail("must specify a base currency '-c' in live "
-                     "execution mode '--live'")
-    else:
-        # check that the start and end dates are passed correctly
-        if start is None and end is None:
-            # check both at the same time to avoid the case where a user
-            # does not pass either of these and then passes the first only
-            # to be told they need to pass the second argument also
-            ctx.fail(
-                "must specify dates with '-s' / '--start' and '-e' / '--end'",
-            )
-        if start is None:
-            ctx.fail("must specify a start date with '-s' / '--start'")
-        if end is None:
-            ctx.fail("must specify an end date with '-e' / '--end'")
-
     if (algotext is not None) == (algofile is not None):
         ctx.fail(
             "must specify exactly one of '-f' / '--algofile' or"
             " '-t' / '--algotext'",
         )
 
+    # check that the start and end dates are passed correctly
+    if start is None and end is None:
+        # check both at the same time to avoid the case where a user
+        # does not pass either of these and then passes the first only
+        # to be told they need to pass the second argument also
+        ctx.fail(
+            "must specify dates with '-s' / '--start' and '-e' / '--end'",
+        )
+    if start is None:
+        ctx.fail("must specify a start date with '-s' / '--start'")
+    if end is None:
+        ctx.fail("must specify an end date with '-e' / '--end'")
+
+    if exchange_name is None:
+        ctx.fail("must specify an exchange name '-x'")
+
     perf = _run(
         initialize=None,
         handle_data=None,
@@ -287,11 +268,11 @@ def run(ctx,
         print_algo=print_algo,
         local_namespace=local_namespace,
         environ=os.environ,
-        live=live,
+        live=False,
         exchange=exchange_name,
         algo_namespace=algo_namespace,
         base_currency=base_currency,
-        live_graph=live_graph
+        live_graph=False
     )
 
     if output == '-':
@@ -335,15 +316,253 @@ def catalyst_magic(line, cell=None):
             raise ValueError('main returned non-zero status code: %d' % e.code)
 
 
+@main.command()
+@click.option(
+    '-f',
+    '--algofile',
+    default=None,
+    type=click.File('r'),
+    help='The file that contains the algorithm to run.',
+)
+@click.option(
+    '-t',
+    '--algotext',
+    help='The algorithm script to run.',
+)
+@click.option(
+    '-D',
+    '--define',
+    multiple=True,
+    help="Define a name to be bound in the namespace before executing"
+         " the algotext. For example '-Dname=value'. The value may be any python"
+         " expression. These are evaluated in order so they may refer to previously"
+         " defined names.",
+)
+@click.option(
+    '-o',
+    '--output',
+    default='-',
+    metavar='FILENAME',
+    show_default=True,
+    help="The location to write the perf data. If this is '-' the perf will"
+         " be written to stdout.",
+)
+@click.option(
+    '--print-algo/--no-print-algo',
+    is_flag=True,
+    default=False,
+    help='Print the algorithm to stdout.',
+)
+@ipython_only(click.option(
+    '--local-namespace/--no-local-namespace',
+    is_flag=True,
+    default=None,
+    help='Should the algorithm methods be resolved in the local namespace.'
+))
+@click.option(
+    '-x',
+    '--exchange-name',
+    type=click.Choice({'bitfinex', 'bittrex', 'poloniex'}),
+    help='The name of the targeted exchange (supported: bitfinex, bittrex, poloniex).',
+)
+@click.option(
+    '-n',
+    '--algo-namespace',
+    help='A label assigned to the algorithm for data storage purposes.'
+)
+@click.option(
+    '-c',
+    '--base-currency',
+    help='The base currency used to calculate statistics '
+         '(e.g. usd, btc, eth).',
+)
+@click.option(
+    '--live-graph/--no-live-graph',
+    is_flag=True,
+    default=False,
+    help='Display live graph.',
+)
+@click.pass_context
+def live(ctx,
+         algofile,
+         algotext,
+         define,
+         output,
+         print_algo,
+         local_namespace,
+         exchange_name,
+         algo_namespace,
+         base_currency,
+         live_graph):
+    """Trade live with the given algorithm.
+    """
+    if (algotext is not None) == (algofile is not None):
+        ctx.fail(
+            "must specify exactly one of '-f' / '--algofile' or"
+            " '-t' / '--algotext'",
+        )
+
+    if exchange_name is None:
+        ctx.fail("must specify an exchange name '-x'")
+    if algo_namespace is None:
+        ctx.fail("must specify an algorithm name '-n' in live execution mode")
+    if base_currency is None:
+        ctx.fail("must specify a base currency '-c' in live execution mode")
+
+    perf = _run(
+        initialize=None,
+        handle_data=None,
+        before_trading_start=None,
+        analyze=None,
+        algofile=algofile,
+        algotext=algotext,
+        defines=define,
+        data_frequency=None,
+        capital_base=None,
+        data=None,
+        bundle=None,
+        bundle_timestamp=None,
+        start=None,
+        end=None,
+        output=output,
+        print_algo=print_algo,
+        local_namespace=local_namespace,
+        environ=os.environ,
+        live=True,
+        exchange=exchange_name,
+        algo_namespace=algo_namespace,
+        base_currency=base_currency,
+        live_graph=live_graph
+    )
+
+    if output == '-':
+        click.echo(str(perf))
+    elif output != os.devnull:  # make the catalyst magic not write any data
+        perf.to_pickle(output)
+
+    return perf
+
+
+@main.command(name='ingest-exchange')
+@click.option(
+    '-x',
+    '--exchange-name',
+    type=click.Choice({'bitfinex', 'bittrex', 'poloniex'}),
+    help='The name of the exchange bundle to ingest (supported: bitfinex,'
+         ' bittrex, poloniex).',
+)
+@click.option(
+    '-f',
+    '--data-frequency',
+    type=click.Choice({'daily', 'minute', 'daily,minute', 'minute,daily'}),
+    default='daily',
+    show_default=True,
+    help='The data frequency of the desired OHLCV bars.',
+)
+@click.option(
+    '-s',
+    '--start',
+    default=None,
+    type=Date(tz='utc', as_timestamp=True),
+    help='The start date of the data range. (default: one year from end date)',
+)
+@click.option(
+    '-e',
+    '--end',
+    default=None,
+    type=Date(tz='utc', as_timestamp=True),
+    help='The end date of the data range. (default: today)',
+)
+@click.option(
+    '-i',
+    '--include-symbols',
+    default=None,
+    help='A list of symbols to ingest (optional comma separated list)',
+)
+@click.option(
+    '--exclude-symbols',
+    default=None,
+    help='A list of symbols to exclude from the ingestion '
+         '(optional comma separated list)',
+)
+@click.option(
+    '--show-progress/--no-show-progress',
+    default=True,
+    help='Print progress information to the terminal.'
+)
+def ingest_exchange(exchange_name, data_frequency, start, end,
+                    include_symbols, exclude_symbols, show_progress):
+    """
+    Ingest data for the given exchange.
+    """
+
+    if exchange_name is None:
+        ctx.fail("must specify an exchange name '-x'")
+
+    exchange = get_exchange(exchange_name)
+    exchange_bundle = ExchangeBundle(exchange)
+
+    click.echo('Ingesting exchange bundle {}...'.format(exchange_name))
+    exchange_bundle.ingest(
+        data_frequency=data_frequency,
+        include_symbols=include_symbols,
+        exclude_symbols=exclude_symbols,
+        start=start,
+        end=end,
+        show_progress=show_progress
+    )
+
+
+@main.command(name='clean-exchange')
+@click.option(
+    '-x',
+    '--exchange-name',
+    type=click.Choice({'bitfinex', 'bittrex', 'poloniex'}),
+    help='The name of the exchange bundle to ingest (supported: bitfinex,'
+         ' bittrex, poloniex).',
+)
+@click.option(
+    '-f',
+    '--data-frequency',
+    type=click.Choice({'daily', 'minute'}),
+    default=None,
+    help='The bundle data frequency to remove. If not specified, it will '
+         'remove both daily and minute bundles.',
+)
+@click.pass_context
+def clean_exchange(ctx, exchange_name, data_frequency):
+    """Clean up bundles from 'ingest-exchange'.
+    """
+
+    if exchange_name is None:
+        ctx.fail("must specify an exchange name '-x'")
+
+    exchange = get_exchange(exchange_name)
+    exchange_bundle = ExchangeBundle(exchange)
+
+    click.echo('Cleaning exchange bundle {}...'.format(exchange_name))
+    exchange_bundle.clean(
+        data_frequency=data_frequency,
+    )
+    click.echo('Done')
+
+
 @main.command()
 @click.option(
     '-b',
     '--bundle',
-    default='poloniex',
     metavar='BUNDLE-NAME',
-    show_default=True,
+    default=None,
+    show_default=False,
     help='The data bundle to ingest.',
 )
+@click.option(
+    '-x',
+    '--exchange-name',
+    type=click.Choice({'bitfinex', 'bittrex', 'poloniex'}),
+    help='The name of the exchange bundle to ingest (supported: bitfinex,'
+         ' bittrex, poloniex).',
+)
 @click.option(
     '-c',
     '--compile-locally',
@@ -362,9 +581,12 @@ def catalyst_magic(line, cell=None):
     default=True,
     help='Print progress information to the terminal.'
 )
-def ingest(bundle, compile_locally, assets_version, show_progress):
+@click.pass_context
+def ingest(ctx, bundle, exchange_name, compile_locally, assets_version,
+           show_progress):
     """Ingest the data for the given bundle.
     """
+
     bundles_module.ingest(
         bundle,
         os.environ,
@@ -384,6 +606,13 @@ def ingest(bundle, compile_locally, assets_version, show_progress):
     show_default=True,
     help='The data bundle to clean.',
 )
+@click.option(
+    '-x',
+    '--exchange_name',
+    metavar='EXCHANGE-NAME',
+    show_default=True,
+    help='The exchange bundle name to clean.',
+)
 @click.option(
     '-e',
     '--before',
@@ -407,7 +636,7 @@ def ingest(bundle, compile_locally, assets_version, show_progress):
          ' This may not be passed with -e / --before or -a / --after',
 )
 def clean(bundle, before, after, keep_last):
-    """Clean up data downloaded with the ingest command.
+    """Clean up bundles from 'ingest'.
     """
     bundles_module.clean(
         bundle,

catalyst/algorithm.py

@@ -134,15 +134,13 @@ from catalyst.utils.security_list import SecurityList
 import catalyst.protocol
 from catalyst.sources.requests_csv import PandasRequestsCSV
 
-from catalyst.gens.sim_engine import (
-    MinuteSimulationClock,
-    FiveMinuteSimulationClock,
-)
+from catalyst.gens.sim_engine import MinuteSimulationClock
 from catalyst.sources.benchmark_source import BenchmarkSource
 from catalyst.catalyst_warnings import ZiplineDeprecationWarning
 
+from catalyst.constants import LOG_LEVEL
 
-log = logbook.Logger("ZiplineLog")
+log = logbook.Logger("CatalystLog", level=LOG_LEVEL)
 
 
 class TradingAlgorithm(object):
@@ -174,7 +172,7 @@ class TradingAlgorithm(object):
     algo_filename : str, optional
         The filename for the algoscript. This will be used in exception
         tracebacks. default: '<string>'.
-    data_frequency : {'daily', '5-minute', 'minute'}, optional
+    data_frequency : {'daily', 'minute'}, optional
         The duration of the bars.
     instant_fill : bool, optional
         Whether to fill orders immediately or on next bar. default: False
@@ -227,7 +225,7 @@ class TradingAlgorithm(object):
             script : str
                 Algoscript that contains initialize and
                 handle_data function definition.
-            data_frequency : {'daily', '5-minute', 'minute'}
+            data_frequency : {'daily', 'minute'}
                The duration of the bars.
             capital_base : float <default: 1.0e5>
                How much capital to start with.
@@ -435,8 +433,6 @@ class TradingAlgorithm(object):
         if get_loader is not None:
             if data_frequency == 'daily':
                 all_dates = self.trading_calendar.all_sessions
-            elif data_frequency == '5-minute':
-                all_dates = self.trading_calendar.all_five_minutes
             elif data_frequency == 'minute':
                 all_dates = self.trading_calendar.all_minutes
             else:
@@ -468,7 +464,7 @@ class TradingAlgorithm(object):
         self._in_before_trading_start = True
 
         with handle_non_market_minutes(data) if \
-                self.data_frequency in ('minute', '5-minute') else ExitStack():
+                self.data_frequency == 'minute' else ExitStack():
             self._before_trading_start(self, data)
 
         self._in_before_trading_start = False
@@ -524,11 +520,10 @@ class TradingAlgorithm(object):
         market_closes = trading_o_and_c['market_close']
         minutely_emission = False
 
-        if self.sim_params.data_frequency in set(('minute', '5-minute')):
+        if self.sim_params.data_frequency == 'minute':
             market_opens = trading_o_and_c['market_open']
 
-            minutely_emission = self.sim_params.emission_rate in \
-                set(('minute', '5-minute'))
+            minutely_emission = self.sim_params.emission_rate == 'minute'
         else:
             # in daily mode, we want to have one bar per session, timestamped
             # as the last minute of the session.
@@ -552,15 +547,6 @@ class TradingAlgorithm(object):
             'UTC',
         )
 
-        if self.sim_params.data_frequency == '5-minute':
-            return FiveMinuteSimulationClock(
-                self.sim_params.sessions,
-                execution_opens,
-                execution_closes,
-                before_trading_start_minutes,
-                minute_emission=minutely_emission,
-            )
-
         return MinuteSimulationClock(
             self.sim_params.sessions,
             execution_opens,
@@ -692,8 +678,6 @@ class TradingAlgorithm(object):
                     time_count = times.nunique()
                     if time_count == 1:
                         self.sim_params.data_frequency = 'daily'
-                    elif time_count == 288:
-                        self.sim_params.data_frequency = '5-minute'
                     else:
                         self.sim_params.data_frequency = 'minute'
 
@@ -715,8 +699,6 @@ class TradingAlgorithm(object):
 
                 if self.sim_params.data_frequency == 'daily':
                     equity_reader_arg = 'equity_daily_reader'
-                elif self.sim_params.data_frequency == '5-minute':
-                    equity_daily_reader = 'equity_5_minute_reader'
                 elif self.sim_params.data_frequency == 'minute':
                     equity_reader_arg = 'equity_minute_reader'
                 equity_reader = PanelBarReader(
@@ -960,9 +942,9 @@ class TradingAlgorithm(object):
                   The arena from the simulation parameters. This will normally
                   be ``'backtest'`` but some systems may use this distinguish
                   live trading from backtesting.
-              data_frequency : {'daily', '5-minute', 'minute'}
+              data_frequency : {'daily', 'minute'}
                   data_frequency tells the algorithm if it is running with
-                  daily, minute, or five-minute mode.
+                  daily or minute mode.
               start : datetime
                   The start date for the simulation.
               end : datetime
@@ -1137,18 +1119,11 @@ class TradingAlgorithm(object):
                           'time_rule= when calling schedule_function without '
                           'specifying a date_rule', stacklevel=3)
 
-        freq = self.sim_params.data_frequency
-
         date_rule = date_rule or date_rules.every_day()
-        if freq is 'daily':
-            # ignore time rule in daily mode
-            time_rule = time_rules.every_minute()
-        else:
-            # use provided time rule or default to every minute or 5 minutes
-            # based on desired data frequency.
-            time_rule = time_rule or (time_rules.every_5_minutes()
-                                      if freq is '5-minute' else
-                                      time_rules.every_minute())
+        time_rule = ((time_rule or time_rules.every_minute())
+                     if self.sim_params.data_frequency == 'minute' else
+                     # If we are in daily mode the time_rule is ignored.
+                     time_rules.every_minute())
 
         # Check the type of the algorithm's schedule before pulling calendar
         # Note that the ExchangeTradingSchedule is currently the only
@@ -1819,7 +1794,7 @@ class TradingAlgorithm(object):
 
     @data_frequency.setter
     def data_frequency(self, value):
-        assert value in ('daily', '5-minute', 'minute')
+        assert value in ('daily', 'minute')
         self.sim_params.data_frequency = value
 
     @api_method

catalyst/assets/_assets.pyx

@@ -17,6 +17,8 @@
 """
 Cythonized Asset object.
 """
+import hashlib
+
 cimport cython
 from cpython.number cimport PyNumber_Index
 from cpython.object cimport (
@@ -395,6 +397,9 @@ cdef class TradingPair(Asset):
     cdef readonly float leverage
     cdef readonly object market_currency
     cdef readonly object base_currency
+    cdef readonly object end_daily
+    cdef readonly object end_minute
+    cdef readonly object exchange_symbol
 
     _kwargnames = frozenset({
         'sid',
@@ -408,7 +413,11 @@ cdef class TradingPair(Asset):
         'exchange_full',
         'leverage',
         'market_currency',
-        'base_currency'
+        'base_currency',
+        'end_daily',
+        'end_minute',
+        'exchange_symbol',
+        'min_trade_size'
     })
     def __init__(self,
                  object symbol,
@@ -417,10 +426,14 @@ cdef class TradingPair(Asset):
                  object asset_name=None,
                  int sid=0,
                  float leverage=1.0,
+                 object end_daily=None,
+                 object end_minute=None,
                  object end_date=None,
+                 object exchange_symbol=None,
                  object first_traded=None,
                  object auto_close_date=None,
-                 object exchange_full=None):
+                 object exchange_full=None,
+                 object min_trade_size=None):
         """
         Replicates the Asset constructor with some built-in conventions
         and a new 'leverage' attribute.
@@ -472,10 +485,14 @@ cdef class TradingPair(Asset):
         :param asset_name:
         :param sid:
         :param leverage:
+        :param end_daily
+        :param end_minute
         :param end_date:
+        :param exchange_symbol:
         :param first_traded:
         :param auto_close_date:
         :param exchange_full:
+        :param min_trade_size:
         """
 
         symbol = symbol.lower()
@@ -486,7 +503,11 @@ cdef class TradingPair(Asset):
 
         if sid == 0 or sid is None:
             try:
-                sid = abs(hash(symbol)) % (10 ** 4)
+                # sid = abs(hash(symbol)) % (10 ** 4)
+                # TODO: try to encode the symbol in the main scope
+                sid = int(
+                    hashlib.sha256(symbol.encode('utf-8')).hexdigest(), 16
+                ) % 10 ** 6
             except Exception as e:
                 raise SidHashError(symbol=symbol)
 
@@ -509,25 +530,49 @@ cdef class TradingPair(Asset):
             first_traded=first_traded,
             auto_close_date=auto_close_date,
             exchange_full=exchange_full,
+            min_trade_size=min_trade_size
         )
 
         self.leverage = leverage
+        self.end_daily = end_daily
+        self.end_minute = end_minute
+        self.exchange_symbol = exchange_symbol
 
     def __repr__(self):
         return 'Trading Pair {symbol}({sid}) Exchange: {exchange}, ' \
                'Introduced On: {start_date}, ' \
                'Market Currency: {market_currency}, ' \
                'Base Currency: {base_currency}, ' \
-               'Exchange Leverage: {leverage}'.format(
+               'Exchange Leverage: {leverage}, ' \
+               'Minimum Trade Size: {min_trade_size} ' \
+               'Last daily ingestion: {end_daily} ' \
+               'Last minutely ingestion: {end_minute}'.format(
             symbol=self.symbol,
             sid=self.sid,
             exchange=self.exchange,
             start_date=self.start_date,
             market_currency=self.market_currency,
             base_currency=self.base_currency,
-            leverage=self.leverage
+            leverage=self.leverage,
+            min_trade_size=self.min_trade_size,
+            end_daily=self.end_daily,
+            end_minute=self.end_minute
         )
 
+    def is_exchange_open(self, dt_minute):
+        """
+        Parameters
+        ----------
+        dt_minute: pd.Timestamp (UTC, tz-aware)
+            The minute to check.
+
+        Returns
+        -------
+        boolean: whether the asset's exchange is open at the given minute.
+        """
+        #TODO: consider implementing to spot holds
+        return True
+
     cpdef __reduce__(self):
         """
         Function used by pickle to determine how to serialize/deserialize this
@@ -544,7 +589,8 @@ cdef class TradingPair(Asset):
                                  self.end_date,
                                  self.first_traded,
                                  self.auto_close_date,
-                                 self.exchange_full))
+                                 self.exchange_full,
+                                 self.min_trade_size))
 
 def make_asset_array(int size, Asset asset):
     cdef np.ndarray out = np.empty([size], dtype=object)

catalyst/assets/assets.py

@@ -76,7 +76,9 @@ from catalyst.utils.numpy_utils import as_column
 from catalyst.utils.preprocess import preprocess
 from catalyst.utils.sqlite_utils import group_into_chunks, coerce_string_to_eng
 
-log = Logger('assets.py')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('assets.py', level=LOG_LEVEL)
 
 # A set of fields that need to be converted to strings before building an
 # Asset to avoid unicode fields

catalyst/constants.py

@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+
+import logbook
+
+LOG_LEVEL = logbook.INFO

catalyst/curate/poloniex.py

@@ -2,10 +2,13 @@ import json, time, csv
 from datetime import datetime
 import pandas as pd
 import os, time, shutil, requests, logbook
+from catalyst.exchange.exchange_utils import get_exchange_symbols_filename
+
 
 DT_START        = int(time.mktime(datetime(2010, 1, 1, 0, 0).timetuple()))
 DT_END          = int(time.time())
 CSV_OUT_FOLDER  = '/var/tmp/catalyst/data/poloniex/'
+CSV_OUT_FOLDER  = '/Volumes/enigma/data/poloniex/'
 CONN_RETRIES    = 2
 
 logbook.StderrHandler().push_application()
@@ -209,32 +212,32 @@ class PoloniexCurator(object):
     def write_ohlcv_file(self, currencyPair):        
         csv_trades = CSV_OUT_FOLDER + 'crypto_trades-' + currencyPair + '.csv'
         csv_1min   = CSV_OUT_FOLDER + 'crypto_1min-' + currencyPair + '.csv'
-        if( os.path.isfile(csv_1min) ):
-            log.debug(currencyPair+': 1min data already present. Delete the file if you want to rebuild it.')
-        else:
-            df = pd.read_csv(csv_trades, names=['tradeID','date','type','rate','amount','total','globalTradeID'], 
-                    dtype = {'tradeID': int, 'date': str, 'type': str, 'rate': float, 'amount': float, 'total': float, 'globalTradeID': int } )
-            df.drop(['tradeID','type','amount','globalTradeID'], axis=1, inplace=True)
-            df['date'] = pd.to_datetime(df['date'], infer_datetime_format=True) 
-            ohlcv = self.generate_ohlcv(df)
-            try: 
-                with open(csv_1min, 'ab') as csvfile:
-                    csvwriter = csv.writer(csvfile)
-                    for item in ohlcv.itertuples():
-                        if item.Index == 0:
-                            continue
-                        csvwriter.writerow([
-                            item.Index.value // 10 ** 9,
-                            item.open,
-                            item.high,
-                            item.low,
-                            item.close,
-                            item.volume,
-                        ])
-            except Exception as e:
-                log.error('Error opening %s' % csv_fn)
-                log.exception(e)
-            log.debug(currencyPair+': Generated 1min OHLCV data.')
+        #if( os.path.isfile(csv_1min) ):
+        #    log.debug(currencyPair+': 1min data already present. Delete the file if you want to rebuild it.')
+        #else:
+        df = pd.read_csv(csv_trades, names=['tradeID','date','type','rate','amount','total','globalTradeID'], 
+                dtype = {'tradeID': int, 'date': str, 'type': str, 'rate': float, 'amount': float, 'total': float, 'globalTradeID': int } )
+        df.drop(['tradeID','type','amount','globalTradeID'], axis=1, inplace=True)
+        df['date'] = pd.to_datetime(df['date'], infer_datetime_format=True) 
+        ohlcv = self.generate_ohlcv(df)
+        try: 
+            with open(csv_1min, 'w') as csvfile:
+                csvwriter = csv.writer(csvfile)
+                for item in ohlcv.itertuples():
+                    if item.Index == 0:
+                        continue
+                    csvwriter.writerow([
+                        item.Index.value // 10 ** 9,
+                        item.open,
+                        item.high,
+                        item.low,
+                        item.close,
+                        item.volume,
+                    ])
+        except Exception as e:
+            log.error('Error opening %s' % csv_fn)
+            log.exception(e)
+        log.debug(currencyPair+': Generated 1min OHLCV data.')
 
 
     '''
@@ -247,11 +250,45 @@ class PoloniexCurator(object):
         df.set_index('date', inplace=True)
         return df[start : end]
 
+    '''
+    Generates a symbols.json file with corresponding start_date for each currencyPair
+    '''
+    def generate_symbols_json(self, filename=None):
+        symbol_map = {}
+
+        if(filename is None):
+            filename = get_exchange_symbols_filename('poloniex')
+
+        with open(filename, 'w') as symbols:
+            for currencyPair in self.currency_pairs:
+                start = None
+                csv_fn     = CSV_OUT_FOLDER + 'crypto_trades-' + currencyPair + '.csv'
+                with open(csv_fn, 'r') as f: 
+                    f.seek(0, os.SEEK_END)
+                    if(f.tell() > 2):                           # First check file is not zero size
+                        f.seek(-2, os.SEEK_END)                 # Jump to the second last byte.
+                        while f.read(1) != b"\n":               # Until EOL is found...
+                            f.seek(-2, os.SEEK_CUR)             # ...jump back the read byte plus one more.
+                        start = pd.to_datetime( f.readline().split(',')[1], infer_datetime_format=True)
+
+                if(start is None):
+                    start = time.gmtime()
+                base, market = currencyPair.lower().split('_')
+                symbol = '{market}_{base}'.format( market=market, base=base )
+                symbol_map[currencyPair] = dict(
+                    symbol = symbol,
+                    start_date = start.strftime("%Y-%m-%d")
+                )
+            json.dump(symbol_map, symbols, sort_keys=True, indent=2, separators=(',',':'))    
+
 
 if __name__ == '__main__':
     pc = PoloniexCurator()
     pc.get_currency_pairs()
+    #pc.generate_symbols_json()
     
     for currencyPair in pc.currency_pairs:
         pc.retrieve_trade_history(currencyPair)
         pc.write_ohlcv_file(currencyPair)
+
+    

catalyst/data/_equities.pyx

@@ -215,13 +215,13 @@ cpdef _read_bcolz_data(ctable_t table,
                 else:
                     continue
 
-        if column_name in ['open', 'high', 'low', 'close']:
+        if column_name in ['open', 'high', 'low', 'close', 'volume']:
             where_nan = (outbuf == 0)
             outbuf_as_float = outbuf.astype(float64) * .000000001
             outbuf_as_float[where_nan] = NAN
             results.append(outbuf_as_float)
-        elif column_name != 'volume':
-            results.append(outbuf.astype(uint32))
+        elif column_name in ['volume']:
+            results.append(outbuf.astype(float64) * .000000001)
         else:
             results.append(outbuf)
     return results

catalyst/data/_minute_bar_internal.pyx

@@ -35,17 +35,6 @@ def minute_value(ndarray[long_t, ndim=1] market_opens,
 
     return market_opens[q] + r
 
-@cython.cdivision(True)
-def five_minute_value(ndarray[long_t, ndim=1] market_opens,
-                      Py_ssize_t pos,
-                      short five_minutes_per_day):
-
-    cdef short q, r
-    q = cython.cdiv(pos, five_minutes_per_day)
-    r = cython.cmod(pos, five_minutes_per_day)
-
-    return market_opens[q] + r
-
 def find_position_of_minute(ndarray[long_t, ndim=1] market_opens,
                             ndarray[long_t, ndim=1] market_closes,
                             long_t minute_val,
@@ -99,26 +88,6 @@ def find_position_of_minute(ndarray[long_t, ndim=1] market_opens,
 
     return (market_open_loc * minutes_per_day) + delta
 
-def find_position_of_five_minute(ndarray[long_t, ndim=1] market_opens,
-                                 ndarray[long_t, ndim=1] market_closes,
-                                 long_t five_minute_val,
-                                 short five_minutes_per_day,
-                                 bool forward_fill):
-
-    cdef Py_ssize_t market_open_loc, market_open, delta
-
-    market_open_loc = \
-        searchsorted(market_opens, five_minute_val, side='right') - 1
-    market_open = market_opens[market_open_loc]
-    market_close = market_closes[market_open_loc]
-
-    if not forward_fill and ((five_minute_val - market_open) >= five_minutes_per_day):
-        raise ValueError("Given five minutes is not between an open and a close")
-
-    delta = int_min(five_minute_val - market_open, market_close - market_open)
-
-    return (market_open_loc * five_minutes_per_day) + delta
-
 def find_last_traded_position_internal(
         ndarray[long_t, ndim=1] market_opens,
         ndarray[long_t, ndim=1] market_closes,
@@ -189,50 +158,3 @@ def find_last_traded_position_internal(
     # found a trade event
     return -1
 
-def find_last_traded_five_minute_position_internal(
-        ndarray[long_t, ndim=1] market_opens,
-        ndarray[long_t, ndim=1] market_closes,
-        long_t end_five_minute,
-        long_t start_five_minute,
-        volumes,
-        short five_minutes_per_day):
-    cdef Py_ssize_t minute_pos, current_minute, q
-
-    five_minute_pos = int_min(
-        find_position_of_five_minute(
-            market_opens,
-            market_closes,
-            end_five_minute,
-            five_minutes_per_day,
-            True,
-        ),
-        len(volumes) - 1,
-    )
-
-    while five_minute_pos >= 0:
-        current_five_minute = five_minute_value(
-            market_opens, five_minute_pos, five_minutes_per_day
-        )
-
-        q = cython.cdiv(five_minute_pos, five_minutes_per_day)
-        if current_five_minute > market_closes[q]:
-            five_minute_pos = find_position_of_five_minute(
-                market_opens,
-                market_closes,
-                market_closes[q],
-                five_minutes_per_day,
-                False,
-            )
-            continue
-
-        if current_five_minute < start_five_minute:
-            return -1
-
-        if volumes[five_minute_pos] != 0:
-            return five_minute_pos
-
-        five_minute_pos -= 1
-
-    # we've gone to the beginning of this asset's range, and still haven't
-    # found a trade event
-    return -1

catalyst/data/bundles/base.py

@@ -30,8 +30,10 @@ from catalyst.utils.cli import (
 )
 from catalyst.utils.memoize import lazyval
 
+from catalyst.constants import LOG_LEVEL
+
 logbook.StderrHandler().push_application()
-log = logbook.Logger(__name__)
+log = logbook.Logger(__name__, level=LOG_LEVEL)
 
 DEFAULT_RETRIES = 5
 
@@ -60,10 +62,6 @@ class BaseBundle(object):
     def minutes_per_day(self):
         raise NotImplementedError()
 
-    @lazyval
-    def five_minutes_per_day(self):
-        raise NotImplementedError()
-
     @lazyval
     def frequencies(self):
         raise NotImplementedError()
@@ -115,7 +113,6 @@ class BaseBundle(object):
                environ,
                asset_db_writer,
                minute_bar_writer,
-               five_minute_bar_writer,
                daily_bar_writer,
                adjustment_writer,
                calendar,
@@ -162,7 +159,7 @@ class BaseBundle(object):
 
                 # Post-process metadata using cached symbol frames, and write to
                 # disk.  This metadata must be written before any attempt to write
-                # either minute or 5-minute data.
+                # minute data.
                 metadata = self._post_process_metadata(
                     raw_metadata,
                     cache,
@@ -170,26 +167,6 @@ class BaseBundle(object):
                 )
                 asset_db_writer.write(metadata)
 
-                # Compile 5-minute symbol data if bundle supports 5-minute mode and
-                # persist the dataset to disk.
-                '''
-                if '5-minute' in self.frequencies:
-                    five_minute_bar_writer.write(
-                        self._fetch_symbol_iter(
-                            api_key,
-                            cache,
-                            symbol_map,
-                            calendar,
-                            start_session,
-                            end_session,
-                            '5-minute',
-                            retries,
-                        ),
-                        length=len(symbol_map),
-                        show_progress=show_progress,
-                    )
-                '''
-
                 # Compile minute symbol data if bundle supports minute mode and
                 # persist the dataset to disk.
                 if 'minute' in self.frequencies:
@@ -491,7 +468,7 @@ class BaseBundle(object):
                     data_frequency,
                 )
                 raw_data.index = pd.to_datetime(raw_data.index, utc=True)
-                raw_data.index = raw_data.index.tz_localize('UTC')
+                #raw_data.index = raw_data.index.tz_localize('UTC')
 
                 # Filter incoming data to fit start and end sessions.
                 raw_data = raw_data[

catalyst/data/bundles/base_pricing.py

@@ -47,10 +47,6 @@ class BaseCryptoPricingBundle(BasePricingBundle):
     def minutes_per_day(self):
         return 1440
 
-    @lazyval
-    def five_minutes_per_day(self):
-        return 288
-
     @property
     def splits(self):
         return []
@@ -68,10 +64,6 @@ class BaseEquityPricingBundle(BasePricingBundle):
     def minutes_per_day(self):
         return 390
 
-    @lazyval
-    def five_minutes_per_day(self):
-        return 78
-
     @property
     def splits(self):
         return self._splits

catalyst/data/bundles/core.py

@@ -17,10 +17,6 @@ from ..us_equity_pricing import (
     SQLiteAdjustmentReader,
     SQLiteAdjustmentWriter,
 )
-from ..five_minute_bars import (
-    BcolzFiveMinuteBarReader,
-    BcolzFiveMinuteBarWriter,
-)
 from ..minute_bars import (
     BcolzMinuteBarReader,
     BcolzMinuteBarWriter,
@@ -54,11 +50,6 @@ def minute_path(bundle_name, timestr, environ=None):
         environ=environ,
     )
 
-def five_minute_path(bundle_name, timestr, environ=None):
-    return pth.data_path(
-        five_minute_relative(bundle_name, timestr, environ),
-        environ=environ,
-    )
 
 def daily_path(bundle_name, timestr, environ=None):
     return pth.data_path(
@@ -92,8 +83,6 @@ def cache_relative(bundle_name, timestr, environ=None):
 def daily_relative(bundle_name, timestr, environ=None):
     return bundle_name, timestr, 'daily_equities.bcolz'
 
-def five_minute_relative(bundle_name, timestr, environ=None):
-    return bundle_name, timestr, 'five_minute.bcolz'
 
 def minute_relative(bundle_name, timestr, environ=None):
     return bundle_name, timestr, 'minute_equities.bcolz'
@@ -206,14 +195,13 @@ RegisteredBundle = namedtuple(
      'start_session',
      'end_session',
      'minutes_per_day',
-     'five_minutes_per_day',
      'ingest',
      'create_writers']
 )
 
 BundleData = namedtuple(
     'BundleData',
-    'asset_finder minute_bar_reader five_minute_bar_reader daily_bar_reader '
+    'asset_finder minute_bar_reader daily_bar_reader '
     'adjustment_reader',
 )
 
@@ -303,7 +291,6 @@ def _make_bundle_core():
             bundle.ingest,
             calendar_name=bundle.calendar_name,
             minutes_per_day=bundle.minutes_per_day,
-            five_minutes_per_day=bundle.five_minutes_per_day,
             start_session=start_session,
             end_session=end_session,
             create_writers=create_writers,
@@ -316,7 +303,6 @@ def _make_bundle_core():
                  start_session=None,
                  end_session=None,
                  minutes_per_day=1440,
-                 five_minutes_per_day=288,
                  create_writers=True):
         """Register a data bundle ingest function.
 
@@ -397,7 +383,6 @@ def _make_bundle_core():
             start_session=start_session,
             end_session=end_session,
             minutes_per_day=minutes_per_day,
-            five_minutes_per_day=five_minutes_per_day,
             ingest=f,
             create_writers=create_writers,
         )
@@ -496,16 +481,6 @@ def _make_bundle_core():
                 # that it can compute the adjustment ratios for the dividends.
                 daily_bar_writer.write(())
 
-                five_minute_bar_writer = BcolzFiveMinuteBarWriter(
-                    wd.ensure_dir(*five_minute_relative(
-                        name, timestr, environ=environ)
-                    ),
-                    calendar,
-                    start_session,
-                    end_session,
-                    five_minutes_per_day=bundle.five_minutes_per_day,
-                )
-
                 minute_bar_writer = BcolzMinuteBarWriter(
                     wd.ensure_dir(*minute_relative(
                         name, timestr, environ=environ)
@@ -532,7 +507,6 @@ def _make_bundle_core():
                 )
             else:
                 daily_bar_writer = None
-                five_minute_bar_writer = None
                 minute_bar_writer = None
                 asset_db_writer = None
                 adjustment_db_writer = None
@@ -544,7 +518,6 @@ def _make_bundle_core():
                 environ,
                 asset_db_writer,
                 minute_bar_writer,
-                five_minute_bar_writer,
                 daily_bar_writer,
                 adjustment_db_writer,
                 calendar,
@@ -631,9 +604,6 @@ def _make_bundle_core():
             minute_bar_reader=BcolzMinuteBarReader(
                 minute_path(name, timestr, environ=environ),
             ),
-            five_minute_bar_reader=BcolzFiveMinuteBarReader(
-                five_minute_path(name, timestr, environ=environ),
-            ),
             daily_bar_reader=BcolzDailyBarReader(
                 daily_path(name, timestr, environ=environ),
             ),

catalyst/data/bundles/poloniex.py

@@ -97,6 +97,8 @@ class PoloniexBundle(BaseCryptoPricingBundle):
                                end_date,
                                frequency):
 
+        # TODO: replace this with direct exchange call
+        # The end date and frequency should be used to calculate the number of bars
         if(frequency == 'minute'):
             pc = PoloniexCurator()
             raw = pc.onemin_to_dataframe(symbol, start_date, end_date)
@@ -146,7 +148,6 @@ class PoloniexBundle(BaseCryptoPricingBundle):
                          data_frequency):
         period_map = {
             'daily': 86400,
-#            '5-minute': 300,
         }
 
         try:
@@ -165,6 +166,7 @@ class PoloniexBundle(BaseCryptoPricingBundle):
         return self._format_polo_query(query_params)
     
     def _format_polo_query(self, query_params):
+        # TODO: got against the exchange object
         return 'https://poloniex.com/public?{query}'.format(
             query=urlencode(query_params),
         )

catalyst/data/bundles/quandl.py

@@ -40,7 +40,9 @@ from catalyst.utils.cli import maybe_show_progress
 
 from . import core as bundles
 
-log = Logger(__name__)
+from catalyst.constants import LOG_LEVEL
+
+log = Logger(__name__, level=LOG_LEVEL)
 seconds_per_call = (pd.Timedelta('10 minutes') / 2000).total_seconds()
 
 class QuandlBundle(BaseEquityPricingBundle):

catalyst/data/data_portal.py

@@ -42,7 +42,6 @@ from catalyst.assets.roll_finder import (
 )
 from catalyst.data.dispatch_bar_reader import (
     AssetDispatchMinuteBarReader,
-    AssetDispatchFiveMinuteBarReader,
     AssetDispatchSessionBarReader
 )
 from catalyst.data.resample import (
@@ -69,7 +68,9 @@ from catalyst.errors import (
     HistoryWindowStartsBeforeData,
 )
 
-log = Logger('DataPortal')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('DataPortal', level=LOG_LEVEL)
 
 BASE_FIELDS = frozenset([
     "open",
@@ -120,10 +121,6 @@ class DataPortal(object):
         daily data backtests or daily history calls in a minute backetest.
         If a daily bar reader is not provided but a minute bar reader is,
         the minutes will be rolled up to serve the daily requests.
-    five_minute_reader : BcolzFiveMinuteBarReader, optional
-        The five minute bar reader for equities. This will be used to service
-        5-minute data backtests or five-minute history calls.  This can be used
-        to serve daily calls if no daily bar reader is provided.
     minute_reader : BcolzMinuteBarReader, optional
         The minute bar reader for equities. This will be used to service
         minute data backtests or minute history calls. This can be used
@@ -150,7 +147,6 @@ class DataPortal(object):
                  trading_calendar,
                  first_trading_day,
                  daily_reader=None,
-                 five_minute_reader=None,
                  minute_reader=None,
                  future_daily_reader=None,
                  future_minute_reader=None,
@@ -202,7 +198,6 @@ class DataPortal(object):
                 reader.last_available_dt
                 for reader in [
                     minute_reader,
-                    five_minute_reader,
                     future_minute_reader,
                 ]
                 if reader is not None
@@ -214,8 +209,6 @@ class DataPortal(object):
 
         aligned_minute_reader = self._ensure_reader_aligned(
             minute_reader)
-        aligned_five_minute_reader = self._ensure_reader_aligned(
-            five_minute_reader)
         aligned_session_reader = self._ensure_reader_aligned(
             daily_reader)
         aligned_future_minute_reader = self._ensure_reader_aligned(
@@ -229,13 +222,10 @@ class DataPortal(object):
         }
 
         aligned_minute_readers = {}
-        aligned_five_minute_readers = {}
         aligned_session_readers = {}
 
         if aligned_minute_reader is not None:
             aligned_minute_readers[Equity] = aligned_minute_reader
-        if aligned_five_minute_reader is not None:
-            aligned_five_minute_readers[Equity] = aligned_five_minute_reader
         if aligned_session_reader is not None:
             aligned_session_readers[Equity] = aligned_session_reader
 
@@ -267,13 +257,6 @@ class DataPortal(object):
             self._last_available_minute,
         )
 
-        _dispatch_five_minute_reader = AssetDispatchFiveMinuteBarReader(
-            self.trading_calendar,
-            self.asset_finder,
-            aligned_five_minute_readers,
-            self._last_available_minute,
-        )
-
         _dispatch_session_reader = AssetDispatchSessionBarReader(
             self.trading_calendar,
             self.asset_finder,
@@ -283,7 +266,6 @@ class DataPortal(object):
 
         self._pricing_readers = {
             'minute': _dispatch_minute_reader,
-            '5-minute': _dispatch_five_minute_reader,
             'daily': _dispatch_session_reader,
         }
 
@@ -719,17 +701,6 @@ class DataPortal(object):
             spot_value=result
         )
 
-
-    def _get_five_minute_spot_value(self, asset, column, dt, ffill=False):
-        return self._get_minutely_spot_value(
-            asset,
-            column,
-            dt,
-            ffill, 
-            '5-minute',
-        )
-        
-
     def _get_minute_spot_value(self, asset, column, dt, ffill=False):
         return self._get_minutely_spot_value(
             asset,

catalyst/data/dispatch_bar_reader.py

@@ -18,6 +18,7 @@ from numpy import (
     full,
     nan,
     int64,
+    float64,
     zeros
 )
 from six import iteritems, with_metaclass
@@ -70,7 +71,9 @@ class AssetDispatchBarReader(with_metaclass(ABCMeta)):
         return self._dt_window_size(start_dt, end_dt), num_sids
 
     def _make_raw_array_out(self, field, shape):
-        if field != 'volume' and field != 'sid':
+        if field == 'volume':
+            out = zeros(shape, dtype=float64)
+        elif field != 'sid':
             out = full(shape, nan)
         else:
             out = zeros(shape, dtype=int64)
@@ -135,12 +138,6 @@ class AssetDispatchMinuteBarReader(AssetDispatchBarReader):
     def _dt_window_size(self, start_dt, end_dt):
         return len(self.trading_calendar.minutes_in_range(start_dt, end_dt))
 
-
-class AssetDispatchFiveMinuteBarReader(AssetDispatchBarReader):
-
-    def _dt_window_size(self, start_dt, end_dt):
-        return len(self.trading_calendar.five_minutes_in_range(start_dt, end_dt))
-
 class AssetDispatchSessionBarReader(AssetDispatchBarReader):
 
     def _dt_window_size(self, start_dt, end_dt):

catalyst/data/loader.py

@@ -12,41 +12,38 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import datetime
 import os
 from collections import OrderedDict
 
 import logbook
 import pandas as pd
-import numpy as np
-from pandas_datareader.data import DataReader
-import datetime
-import time
 import pytz
+from pandas_datareader.data import DataReader
 from six import iteritems
 from six.moves.urllib_error import HTTPError
 
-from .benchmarks import get_benchmark_returns
+from catalyst.utils.calendars import get_calendar
 from . import treasuries, treasuries_can
+from .benchmarks import get_benchmark_returns
+from ..utils.deprecate import deprecated
 from ..utils.paths import (
     cache_root,
     data_root,
 )
-from ..utils.deprecate import deprecated
 
-from catalyst.data.bundles.poloniex import PoloniexBundle
-from catalyst.utils.calendars import get_calendar
+from catalyst.constants import LOG_LEVEL
 
-
-logger = logbook.Logger('Loader')
+logger = logbook.Logger('Loader', level=LOG_LEVEL)
 
 # Mapping from index symbol to appropriate bond data
 INDEX_MAPPING = {
     'SPY':
-    (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
+        (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
     '^GSPTSE':
-    (treasuries_can, 'treasury_curves_can.csv', 'bankofcanada.ca'),
+        (treasuries_can, 'treasury_curves_can.csv', 'bankofcanada.ca'),
     '^FTSE':  # use US treasuries until UK bonds implemented
-    (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
+        (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
 }
 
 ONE_HOUR = pd.Timedelta(hours=1)
@@ -94,18 +91,27 @@ def has_data_for_dates(series_or_df, first_date, last_date):
     if not isinstance(dts, pd.DatetimeIndex):
         raise TypeError("Expected a DatetimeIndex, but got %s." % type(dts))
     first, last = dts[[0, -1]].tz_localize(None)
-    return (first <= first_date.tz_localize(None)) and (last >= last_date.tz_localize(None))
+    return (first <= first_date.tz_localize(None)) and (
+        last >= last_date.tz_localize(None))
 
-def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT_BTC',
-                            bundle=None, bundle_data=None, environ=None):
 
+def load_crypto_market_data(trading_day=None, trading_days=None,
+                            bm_symbol=None, bundle=None, bundle_data=None,
+                            environ=None, exchange=None, start_dt=None,
+                            end_dt=None):
     if trading_day is None:
         trading_day = get_calendar('OPEN').trading_day
-    if trading_days is None:
-        trading_days = get_calendar('OPEN').all_sessions
 
-    first_date = trading_days[1]
-    now = pd.Timestamp.utcnow()
+    # TODO: consider making configurable
+    bm_symbol = 'btc_usdt'
+    # if trading_days is None:
+    #    trading_days = get_calendar('OPEN').schedule
+
+    # if start_dt is None:
+    start_dt = get_calendar('OPEN').first_trading_session
+
+    if end_dt is None:
+        end_dt = pd.Timestamp.utcnow()
 
     # We expect to have benchmark and treasury data that's current up until
     # **two** full trading days prior to the most recently completed trading
@@ -121,6 +127,7 @@ def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT
 
     # We'll attempt to download new data if the latest entry in our cache is
     # before this date.
+    '''
     if(bundle_data):
         # If we are using the bundle to retrieve the cryptobenchmark, find the last
         # date for which there is trading data in the bundle
@@ -129,19 +136,31 @@ def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT
         last_date = pd.to_datetime(bundle_data.daily_bar_reader._spot_col('day')[ix],unit='s')
     else:
         last_date = trading_days[trading_days.get_loc(now, method='ffill') - 2]
+    '''
+    last_date = trading_days[trading_days.get_loc(end_dt, method='ffill') - 1]
+
+    if exchange is None:
+        # This is exceptional, since placing the import at the module scope
+        #  breaks things and it's only needed here
+        from catalyst.exchange.poloniex.poloniex import Poloniex
+        exchange = Poloniex('', '', '')
+
+    benchmark_asset = exchange.get_asset(bm_symbol)
+
+    # exchange.get_history_window() already ensures that we have the right data
+    # for the right dates
+    br = exchange.get_history_window(
+        assets=[benchmark_asset],
+        end_dt=last_date,
+        bar_count=pd.Timedelta(last_date - start_dt).days,
+        frequency='1d',
+        field='close',
+        data_frequency='daily')
+    br.columns = ['close']
+    br = br.pct_change(1).iloc[1:]
+    br.loc[start_dt] = 0
+    br = br.sort_index()
 
-    br = ensure_crypto_benchmark_data(
-        bm_symbol,
-        first_date,
-        last_date,
-        now,
-        # We need the trading_day to figure out the close prior to the first
-        # date so that we can compute returns for the first date.
-        trading_day,
-        bundle,
-        bundle_data,
-        environ,
-    )
     # Override first_date for treasury data since we have it for many more years
     # and is independent of crypto data
     first_date_treasury = pd.Timestamp('1990-01-02', tz='UTC')
@@ -149,11 +168,12 @@ def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT
         bm_symbol,
         first_date_treasury,
         last_date,
-        now,
+        end_dt,
         environ,
     )
-    benchmark_returns = br[br.index.slice_indexer(first_date, last_date)]
-    treasury_curves = tc[tc.index.slice_indexer(first_date_treasury, last_date)]
+    benchmark_returns = br[br.index.slice_indexer(start_dt, last_date)]
+    treasury_curves = tc[
+        tc.index.slice_indexer(first_date_treasury, last_date)]
     return benchmark_returns, treasury_curves
 
 
@@ -251,12 +271,11 @@ def ensure_crypto_benchmark_data(symbol,
                                  bundle,
                                  bundle_data,
                                  environ=None):
-
     filename = get_benchmark_filename(symbol)
 
     logger.info(
         ('Loading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
+         'from {first_date} to {last_date}'),
         symbol=symbol,
         first_date=first_date,
         last_date=last_date
@@ -277,7 +296,7 @@ def ensure_crypto_benchmark_data(symbol,
     # If no cached data was found or it was missing any dates then download the
     # necessary data.
 
-    if(bundle == 'poloniex'):
+    if (bundle == 'poloniex'):
         '''
         If we're using the Poloniex bundle, we'll get the benchmark from the bundle
         instead of downloading it from Poloniex every time we need it.
@@ -285,43 +304,51 @@ def ensure_crypto_benchmark_data(symbol,
         prevents users abroad from getting Catalyst to work
         '''
         logger.info(
-            ('Retrieving benchmark data from bundle for {symbol!r} from {first_date} to {last_date}'),
+            (
+                'Retrieving benchmark data from bundle for {symbol!r} from {first_date} to {last_date}'),
             symbol=symbol, first_date=first_date, last_date=last_date)
 
-        asset = bundle_data.asset_finder.lookup_symbol(symbol=symbol,as_of_date=None)
+        asset = bundle_data.asset_finder.lookup_symbol(symbol=symbol,
+                                                       as_of_date=None)
         fields = ['day', 'close']
         raw = bundle_data.daily_bar_reader.load_raw_arrays(
             columns=fields,
             start_date=first_date - trading_day,
             end_date=last_date,
-            assets=[asset,])
-        bench_raw = pd.concat([pd.DataFrame(raw[0], columns=['date']),pd.DataFrame(raw[1], columns=['close'])], axis=1)
-        bench_raw['date'] = pd.to_datetime(bench_raw['date'],unit='s')
+            assets=[asset, ])
+        bench_raw = pd.concat([pd.DataFrame(raw[0], columns=['date']),
+                               pd.DataFrame(raw[1], columns=['close'])],
+                              axis=1)
+        bench_raw['date'] = pd.to_datetime(bench_raw['date'], unit='s')
         bench_raw.set_index('date', inplace=True)
         bench_raw.sort_index(inplace=True)
-        bench_raw = bench_raw[pd.to_datetime(first_date - trading_day):pd.to_datetime(last_date)]
+        bench_raw = bench_raw[
+                    pd.to_datetime(first_date - trading_day):pd.to_datetime(
+                        last_date)]
 
     else:
         # This is how it used to be: downloading the benchmark everytime. 
         # Leaving this code here to be repurposed in the future for other bundles.
         logger.info(
-            ('Downloading benchmark data for {symbol!r} from {first_date} to {last_date}'),
+            (
+                'Downloading benchmark data for {symbol!r} from {first_date} to {last_date}'),
             symbol=symbol, first_date=first_date, last_date=last_date)
 
+        raise DeprecationWarning('poloniex bundle deprecated')
         # Load benchmark symbol from Poloniex API
-        try:
-            bundle = PoloniexBundle()
-            bench_raw = bundle._fetch_symbol_frame(
-                None,
-                symbol,
-                get_calendar(bundle.calendar_name),
-                first_date - trading_day,
-                last_date,
-                'daily',
-            )
-        except (OSError, IOError, HTTPError):
-            logger.exception('Failed to fetch new crypto benchmark returns')
-            raise
+        # try:
+        #     bundle = PoloniexBundle()
+        #     bench_raw = bundle._fetch_symbol_frame(
+        #         None,
+        #         symbol,
+        #         get_calendar(bundle.calendar_name),
+        #         first_date - trading_day,
+        #         last_date,
+        #         'daily',
+        #     )
+        # except (OSError, IOError, HTTPError):
+        #     logger.exception('Failed to fetch new crypto benchmark returns')
+        #     raise
 
     # select close column and compute percent change between days
     daily_close = bench_raw[['close']]
@@ -380,7 +407,7 @@ def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day,
     # necessary data.
     logger.info(
         ('Downloading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
+         'from {first_date} to {last_date}'),
         symbol=symbol,
         first_date=first_date - trading_day,
         last_date=last_date
@@ -441,7 +468,7 @@ def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day,
     # necessary data.
     logger.info(
         ('Downloading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
+         'from {first_date} to {last_date}'),
         symbol=symbol,
         first_date=first_date - trading_day,
         last_date=last_date
@@ -525,7 +552,8 @@ def _load_cached_data(filename, first_date, last_date, now, resource_name,
             data = pd.DataFrame.from_csv(path)
             if data.empty:
                 raise ValueError("File is empty.")
-            data.index = pd.to_datetime(data.index, infer_datetime_format=True, errors='coerce' ).tz_localize('UTC')
+            data.index = pd.to_datetime(data.index, infer_datetime_format=True,
+                                        errors='coerce').tz_localize('UTC')
             if has_data_for_dates(data, first_date, last_date):
                 return data
 

catalyst/data/minute_bars.py

@@ -39,20 +39,21 @@ from catalyst.data._minute_bar_internal import (
 from catalyst.gens.sim_engine import NANOS_IN_MINUTE
 
 from catalyst.data.bar_reader import BarReader, NoDataOnDate
-from catalyst.data.us_equity_pricing import check_uint32_safe
+from catalyst.data.us_equity_pricing import check_uint64_safe
 from catalyst.utils.calendars import get_calendar
 from catalyst.utils.cli import maybe_show_progress
 from catalyst.utils.memoize import lazyval
 
+from catalyst.constants import LOG_LEVEL
 
-logger = logbook.Logger('MinuteBars')
+logger = logbook.Logger('MinuteBars', level=LOG_LEVEL)
 
 US_EQUITIES_MINUTES_PER_DAY = 390
 FUTURES_MINUTES_PER_DAY = 1440
 
 DEFAULT_EXPECTEDLEN = US_EQUITIES_MINUTES_PER_DAY * 252 * 15
 
-OHLC_RATIO = 1000
+OHLC_RATIO = 100000000
 
 
 class BcolzMinuteOverlappingData(Exception):
@@ -114,15 +115,15 @@ def _sid_subdir_path(sid):
 
 
 def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
-    """Adapt OHLCV columns into uint32 columns.
+    """Adapt OHLCV columns into uint64 columns.
 
     Parameters
     ----------
     cols : dict
         A dict mapping each column name (open, high, low, close, volume)
-        to a float column to convert to uint32.
+        to a float column to convert to uint64.
     scale_factor : int
-        Factor to use to scale float values before converting to uint32.
+        Factor to use to scale float values before converting to uint64.
     sid : int
         Sid of the relevant asset, for logging.
     invalid_data_behavior : str
@@ -135,6 +136,7 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
     scaled_highs = np.nan_to_num(cols['high']) * scale_factor
     scaled_lows = np.nan_to_num(cols['low']) * scale_factor
     scaled_closes = np.nan_to_num(cols['close']) * scale_factor
+    scaled_volumes = np.nan_to_num(cols['volume']) * scale_factor
 
     exclude_mask = np.zeros_like(scaled_opens, dtype=bool)
 
@@ -143,11 +145,12 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
         ('high', scaled_highs),
         ('low', scaled_lows),
         ('close', scaled_closes),
+        ('volume', scaled_volumes),
     ]:
         max_val = scaled_col.max()
 
         try:
-            check_uint32_safe(max_val, col_name)
+            check_uint64_safe(max_val, col_name)
         except ValueError:
             if invalid_data_behavior == 'raise':
                 raise
@@ -155,20 +158,20 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
             if invalid_data_behavior == 'warn':
                 logger.warn(
                     'Values for sid={}, col={} contain some too large for '
-                    'uint32 (max={}), filtering them out',
+                    'uint64 (max={}), filtering them out',
                     sid, col_name, max_val,
                 )
 
             # We want to exclude all rows that have an unsafe value in
             # this column.
-            exclude_mask &= (scaled_col >= np.iinfo(np.uint32).max)
+            exclude_mask &= (scaled_col >= np.iinfo(np.uint64).max)
 
     # Convert all cols to uint32.
-    opens = scaled_opens.astype(np.uint32)
-    highs = scaled_highs.astype(np.uint32)
-    lows = scaled_lows.astype(np.uint32)
-    closes = scaled_closes.astype(np.uint32)
-    volumes = cols['volume'].astype(np.uint32)
+    opens = scaled_opens.astype(np.uint64)
+    highs = scaled_highs.astype(np.uint64)
+    lows = scaled_lows.astype(np.uint64)
+    closes = scaled_closes.astype(np.uint64)
+    volumes = scaled_volumes.astype(np.uint64)
 
     # Exclude rows with unsafe values by setting to zero.
     opens[exclude_mask] = 0
@@ -260,14 +263,14 @@ class BcolzMinuteBarMetadata(object):
             )
 
     def __init__(
-        self,
-        default_ohlc_ratio,
-        ohlc_ratios_per_sid,
-        calendar,
-        start_session,
-        end_session,
-        minutes_per_day,
-        version=FORMAT_VERSION,
+            self,
+            default_ohlc_ratio,
+            ohlc_ratios_per_sid,
+            calendar,
+            start_session,
+            end_session,
+            minutes_per_day,
+            version=FORMAT_VERSION,
     ):
         self.calendar = calendar
         self.start_session = start_session
@@ -288,7 +291,7 @@ class BcolzMinuteBarMetadata(object):
         ohlc_ratio : int
             The default ratio by which to multiply the pricing data to
             convert the floats from floats to an integer to fit within
-            the np.uint32. If ohlc_ratios_per_sid is None or does not
+            the np.uint64. If ohlc_ratios_per_sid is None or does not
             contain a mapping for a given sid, this ratio is used.
         ohlc_ratios_per_sid : dict
              A dict mapping each sid in the output to the factor by
@@ -340,10 +343,10 @@ class BcolzMinuteBarMetadata(object):
             'first_trading_day': str(self.start_session.date()),
             'market_opens': (
                 market_opens.values.astype('datetime64[m]').
-                astype(np.int64).tolist()),
+                    astype(np.int64).tolist()),
             'market_closes': (
                 market_closes.values.astype('datetime64[m]').
-                astype(np.int64).tolist()),
+                    astype(np.int64).tolist()),
         }
         with open(self.metadata_path(rootdir), 'w+') as fp:
             json.dump(metadata, fp)
@@ -372,13 +375,13 @@ class BcolzMinuteBarWriter(object):
         The last trading session in the data set.
     default_ohlc_ratio : int, optional
         The default ratio by which to multiply the pricing data to
-        convert from floats to integers that fit within np.uint32. If
+        convert from floats to integers that fit within np.uint64. If
         ohlc_ratios_per_sid is None or does not contain a mapping for a
-        given sid, this ratio is used. Default is OHLC_RATIO (1000).
+        given sid, this ratio is used. Default is OHLC_RATIO (10^8).
     ohlc_ratios_per_sid : dict, optional
         A dict mapping each sid in the output to the ratio by which to
         multiply the pricing data to convert the floats from floats to
-        an integer to fit within the np.uint32.
+        an integer to fit within the np.uint64.
     expectedlen : int, optional
         The expected length of the dataset, used when creating the initial
         bcolz ctable.
@@ -401,11 +404,9 @@ class BcolzMinuteBarWriter(object):
     Each individual asset's data is stored as a bcolz table with a column for
     each pricing field: (open, high, low, close, volume)
 
-    The open, high, low, and close columns are integers which are 1000 times
+    The open, high, low, close and volume columns are integers which are 10^8 times
     the quoted price, so that the data can represented and stored as an
-    np.uint32, supporting market prices quoted up to the thousands place.
-
-    volume is a np.uint32 with no mutation of the tens place.
+    np.uint64, supporting market prices quoted up to the 1/10^8-th place.
 
     The 'index' for each individual asset are a repeating period of minutes of
     length `minutes_per_day` starting from each market open.
@@ -573,7 +574,7 @@ class BcolzMinuteBarWriter(object):
         if not os.path.exists(sid_containing_dirname):
             # Other sids may have already created the containing directory.
             os.makedirs(sid_containing_dirname)
-        initial_array = np.empty(0, np.uint32)
+        initial_array = np.empty(0, np.uint64)
         table = ctable(
             rootdir=path,
             columns=[
@@ -610,7 +611,7 @@ class BcolzMinuteBarWriter(object):
         minute_offset = len(table) % self._minutes_per_day
         num_to_prepend = numdays * self._minutes_per_day - minute_offset
 
-        prepend_array = np.zeros(num_to_prepend, np.uint32)
+        prepend_array = np.zeros(num_to_prepend, np.uint64)
         # Fill all OHLCV with zeros.
         table.append([prepend_array] * 5)
         table.flush()
@@ -815,11 +816,11 @@ class BcolzMinuteBarWriter(object):
 
         minutes_count = all_minutes_in_window.size
 
-        open_col = np.zeros(minutes_count, dtype=np.uint32)
-        high_col = np.zeros(minutes_count, dtype=np.uint32)
-        low_col = np.zeros(minutes_count, dtype=np.uint32)
-        close_col = np.zeros(minutes_count, dtype=np.uint32)
-        vol_col = np.zeros(minutes_count, dtype=np.uint32)
+        open_col = np.zeros(minutes_count, dtype=np.uint64)
+        high_col = np.zeros(minutes_count, dtype=np.uint64)
+        low_col = np.zeros(minutes_count, dtype=np.uint64)
+        close_col = np.zeros(minutes_count, dtype=np.uint64)
+        vol_col = np.zeros(minutes_count, dtype=np.uint64)
 
         dt_ixs = np.searchsorted(all_minutes_in_window.values,
                                  dts.astype('datetime64[ns]'))
@@ -914,10 +915,10 @@ class BcolzMinuteBarReader(MinuteBarReader):
         )
         self._schedule = self.calendar.schedule[slicer]
         self._market_opens = self._schedule.market_open
-        self._market_open_values = self._market_opens.values.\
+        self._market_open_values = self._market_opens.values. \
             astype('datetime64[m]').astype(np.int64)
         self._market_closes = self._schedule.market_close
-        self._market_close_values = self._market_closes.values.\
+        self._market_close_values = self._market_closes.values. \
             astype('datetime64[m]').astype(np.int64)
 
         self._default_ohlc_inverse = 1.0 / metadata.default_ohlc_ratio
@@ -1125,8 +1126,8 @@ class BcolzMinuteBarReader(MinuteBarReader):
             else:
                 return np.nan
 
-        if field != 'volume':
-            value *= self._ohlc_ratio_inverse_for_sid(sid)
+        # if field != 'volume':
+        value *= self._ohlc_ratio_inverse_for_sid(sid)
         return value
 
     def get_last_traded_dt(self, asset, dt):
@@ -1248,7 +1249,7 @@ class BcolzMinuteBarReader(MinuteBarReader):
             if field != 'volume':
                 out = np.full(shape, np.nan)
             else:
-                out = np.zeros(shape, dtype=np.uint32)
+                out = np.zeros(shape, dtype=np.float64)
 
             for i, sid in enumerate(sids):
                 carray = self._open_minute_file(field, sid)
@@ -1256,17 +1257,17 @@ class BcolzMinuteBarReader(MinuteBarReader):
                 if indices_to_exclude is not None:
                     for excl_start, excl_stop in indices_to_exclude[::-1]:
                         excl_slice = np.s_[
-                            excl_start - start_idx:excl_stop - start_idx + 1]
+                                     excl_start - start_idx:excl_stop - start_idx + 1]
                         values = np.delete(values, excl_slice)
 
                 where = values != 0
                 # first slice down to len(where) because we might not have
                 # written data for all the minutes requested
-                if field != 'volume':
-                    out[:len(where), i][where] = (
-                        values[where] * self._ohlc_ratio_inverse_for_sid(sid))
-                else:
-                    out[:len(where), i][where] = values[where]
+                # if field != 'volume':
+                out[:len(where), i][where] = (
+                    values[where] * self._ohlc_ratio_inverse_for_sid(sid))
+                # else:
+                #    out[:len(where), i][where] = values[where]
 
             results.append(out)
         return results
@@ -1319,9 +1320,9 @@ class H5MinuteBarUpdateWriter(object):
 
     def __init__(self, path, complevel=None, complib=None):
         self._complevel = complevel if complevel \
-            is not None else self._COMPLEVEL
+                                       is not None else self._COMPLEVEL
         self._complib = complib if complib \
-            is not None else self._COMPLIB
+                                   is not None else self._COMPLIB
         self._path = path
 
     def write(self, frames):
@@ -1353,6 +1354,7 @@ class H5MinuteBarUpdateReader(MinuteBarUpdateReader):
     path : str
         The path of the HDF5 file from which to source data.
     """
+
     def __init__(self, path):
         self._panel = pd.read_hdf(path)
 

catalyst/data/us_equity_pricing.py

@@ -83,7 +83,9 @@ from catalyst.utils.cli import (
 from ._equities import _compute_row_slices, _read_bcolz_data
 from ._adjustments import load_adjustments_from_sqlite
 
-logger = logbook.Logger('UsEquityPricing')
+from catalyst.constants import LOG_LEVEL
+
+logger = logbook.Logger('UsEquityPricing', level=LOG_LEVEL)
 
 OHLC = frozenset(['open', 'high', 'low', 'close'])
 OHLCV = frozenset(['open', 'high', 'low', 'close', 'volume'])
@@ -441,7 +443,7 @@ class BcolzDailyBarWriter(object):
         dates = raw_data.index.values.astype('datetime64[s]')
         check_uint32_safe(dates.max().view(np.int64), 'day')
         processed['day'] = dates.astype('uint32')
-        processed['volume'] = raw_data.volume.astype('uint64')
+        processed['volume'] = (raw_data.volume * PRICE_ADJUSTMENT_FACTOR).astype('uint64')
         return ctable.fromdataframe(processed)
 
 
@@ -494,9 +496,8 @@ class BcolzDailyBarReader(SessionBarReader):
 
     The data in these columns is interpreted as follows:
 
-    - Price columns ('open', 'high', 'low', 'close') are interpreted as 1000 *
-      as-traded dollar value.
-    - Volume is interpreted as as-traded volume.
+    - Price columns ('open', 'high', 'low', 'close') and Volume are interpreted 
+      as 10^9 * as-traded dollar value.
     - Day is interpreted as seconds since midnight UTC, Jan 1, 1970.
     - Id is the asset id of the row.
 
@@ -762,13 +763,10 @@ class BcolzDailyBarReader(SessionBarReader):
         """
         ix = self.sid_day_index(sid, dt)
         price = self._spot_col(field)[ix]
-        if field != 'volume':
-            if price == 0:
-                return nan
-            else:
-                return price / PRICE_ADJUSTMENT_FACTOR
+        if field != 'volume' and price == 0:
+            return nan
         else:
-            return price
+            return price / PRICE_ADJUSTMENT_FACTOR
 
 
 class PanelBarReader(SessionBarReader):

catalyst/examples/arbitrage_with_interface.py

@@ -0,0 +1,275 @@
+from logbook import Logger
+
+from catalyst.api import (
+    record,
+    order,
+    symbol,
+    get_open_orders
+)
+from catalyst.exchange.stats_utils import get_pretty_stats
+from catalyst.utils.run_algo import run_algorithm
+
+algo_namespace = 'arbitrage_eth_btc'
+log = Logger(algo_namespace)
+
+
+def initialize(context):
+    log.info('initializing arbitrage algorithm')
+
+    # The context contains a new "exchanges" attribute which is a dictionary
+    # of exchange objects by exchange name. This allow easy access to the
+    # exchanges.
+    context.buying_exchange = context.exchanges['poloniex']
+    context.selling_exchange = context.exchanges['bitfinex']
+
+    context.trading_pair_symbol = 'eth_btc'
+    context.trading_pairs = dict()
+
+    # Note the second parameter of the symbol() method
+    # Passing the exchange name here returns a TradingPair object including
+    # the exchange information. This allow all other operations using
+    # the TradingPair to target the correct exchange.
+    context.trading_pairs[context.buying_exchange] = \
+        symbol('eth_btc', context.buying_exchange.name)
+
+    context.trading_pairs[context.selling_exchange] = \
+        symbol(context.trading_pair_symbol, context.selling_exchange.name)
+
+    context.entry_points = [
+        dict(gap=0.03, amount=0.05),
+        dict(gap=0.04, amount=0.1),
+        dict(gap=0.05, amount=0.5),
+    ]
+    context.exit_points = [
+        dict(gap=-0.02, amount=0.5),
+    ]
+
+    context.SLIPPAGE_ALLOWED = 0.02
+    pass
+
+
+def place_orders(context, amount, buying_price, selling_price, action):
+    """
+    This method will always place two orders of the same amount to keep
+    the currency position the same as it moves between the two exchanges.
+
+    :param context: TradingAlgorithm
+    :param amount: float
+        The trading pair amount to trade on both exchanges.
+    :param buying_price: float
+        The current trading pair price on the buying exchange.
+    :param selling_price: float
+        The current trading pair price on the selling exchange.
+    :param action: string
+        "enter": buys on the buying exchange and sells on the selling exchange
+        "exit": buys on the selling exchange and sells on the buying exchange
+
+    :return:
+    """
+    if action == 'enter':
+        enter_exchange = context.buying_exchange
+        entry_price = buying_price
+
+        exit_exchange = context.selling_exchange
+        exit_price = selling_price
+
+    elif action == 'exit':
+        enter_exchange = context.selling_exchange
+        entry_price = selling_price
+
+        exit_exchange = context.buying_exchange
+        exit_price = buying_price
+
+    else:
+        raise ValueError('invalid order action')
+
+    base_currency = enter_exchange.base_currency
+    base_currency_amount = enter_exchange.portfolio.cash
+
+    exit_balances = exit_exchange.get_balances()
+    exit_currency = context.trading_pairs[
+        context.selling_exchange].market_currency
+
+    if exit_currency in exit_balances:
+        market_currency_amount = exit_balances[exit_currency]
+    else:
+        log.warn(
+            'the selling exchange {exchange_name} does not hold '
+            'currency {currency}'.format(
+                exchange_name=exit_exchange.name,
+                currency=exit_currency
+            )
+        )
+        return
+
+    if base_currency_amount < (amount * entry_price):
+        adj_amount = base_currency_amount / entry_price
+        log.warn(
+            'not enough {base_currency} ({base_currency_amount}) to buy '
+            '{amount}, adjusting the amount to {adj_amount}'.format(
+                base_currency=base_currency,
+                base_currency_amount=base_currency_amount,
+                amount=amount,
+                adj_amount=adj_amount
+            )
+        )
+        amount = adj_amount
+
+    elif market_currency_amount < amount:
+        log.warn(
+            'not enough {currency} ({currency_amount}) to sell '
+            '{amount}, aborting'.format(
+                currency=exit_currency,
+                currency_amount=market_currency_amount,
+                amount=amount
+            )
+        )
+        return
+
+    adj_buy_price = entry_price * (1 + context.SLIPPAGE_ALLOWED)
+    log.info(
+        'buying {amount} {trading_pair} on {exchange_name} with price '
+        'limit {limit_price}'.format(
+            amount=amount,
+            trading_pair=context.trading_pair_symbol,
+            exchange_name=enter_exchange.name,
+            limit_price=adj_buy_price
+        )
+    )
+    order(
+        asset=context.trading_pairs[enter_exchange],
+        amount=amount,
+        limit_price=adj_buy_price
+    )
+
+    adj_sell_price = exit_price * (1 - context.SLIPPAGE_ALLOWED)
+    log.info(
+        'selling {amount} {trading_pair} on {exchange_name} with price '
+        'limit {limit_price}'.format(
+            amount=-amount,
+            trading_pair=context.trading_pair_symbol,
+            exchange_name=exit_exchange.name,
+            limit_price=adj_sell_price
+        )
+    )
+    order(
+        asset=context.trading_pairs[exit_exchange],
+        amount=-amount,
+        limit_price=adj_sell_price
+    )
+    pass
+
+
+def handle_data(context, data):
+    log.info('handling bar {}'.format(data.current_dt))
+
+    buying_price = data.current(
+        context.trading_pairs[context.buying_exchange], 'price')
+
+    log.info('price on buying exchange {exchange}: {price}'.format(
+        exchange=context.buying_exchange.name.upper(),
+        price=buying_price,
+    ))
+
+    selling_price = data.current(
+        context.trading_pairs[context.selling_exchange], 'price')
+
+    log.info('price on selling exchange {exchange}: {price}'.format(
+        exchange=context.selling_exchange.name.upper(),
+        price=selling_price,
+    ))
+
+    # If for example,
+    #   selling price = 50
+    #   buying price = 25
+    #   expected gap = 1
+
+    # If follows that,
+    #   selling price - buying price / buying price
+    #   50 - 25 / 25 = 1
+    gap = (selling_price - buying_price) / buying_price
+    log.info(
+        'the price gap: {gap} ({gap_percent}%)'.format(
+            gap=gap,
+            gap_percent=gap * 100
+        )
+    )
+    record(buying_price=buying_price, selling_price=selling_price, gap=gap)
+
+    # Waiting for orders to close before initiating new ones
+    for exchange in context.trading_pairs:
+        asset = context.trading_pairs[exchange]
+
+        orders = get_open_orders(asset)
+        if orders:
+            log.info(
+                'found {order_count} open orders on {exchange_name} '
+                'skipping bar until all open orders execute'.format(
+                    order_count=len(orders),
+                    exchange_name=exchange.name
+                )
+            )
+            return
+
+    # Consider the least ambitious entry point first
+    # Override of wider gap is found
+    entry_points = sorted(
+        context.entry_points,
+        key=lambda point: point['gap'],
+    )
+
+    buy_amount = None
+    for entry_point in entry_points:
+        if gap > entry_point['gap']:
+            buy_amount = entry_point['amount']
+
+    if buy_amount:
+        log.info('found buy trigger for amount: {}'.format(buy_amount))
+        place_orders(
+            context=context,
+            amount=buy_amount,
+            buying_price=buying_price,
+            selling_price=selling_price,
+            action='enter'
+        )
+
+    else:
+        # Consider the narrowest exit gap first
+        # Override of wider gap is found
+        exit_points = sorted(
+            context.exit_points,
+            key=lambda point: point['gap'],
+            reverse=True
+        )
+
+        sell_amount = None
+        for exit_point in exit_points:
+            if gap < exit_point['gap']:
+                sell_amount = exit_point['amount']
+
+        if sell_amount:
+            log.info('found sell trigger for amount: {}'.format(sell_amount))
+            place_orders(
+                context=context,
+                amount=sell_amount,
+                buying_price=buying_price,
+                selling_price=selling_price,
+                action='exit'
+            )
+
+
+def analyze(context, stats):
+    log.info('the daily stats:\n{}'.format(get_pretty_stats(stats)))
+    pass
+
+
+run_algorithm(
+    initialize=initialize,
+    handle_data=handle_data,
+    analyze=analyze,
+    exchange_name='poloniex,bitfinex',
+    live=True,
+    algo_namespace=algo_namespace,
+    base_currency='btc',
+    live_graph=False
+)

catalyst/examples/buy_and_hodl.py

@@ -24,7 +24,7 @@ from catalyst.api import (
 )
 
 def initialize(context):
-    context.ASSET_NAME = 'USDT_BTC'
+    context.ASSET_NAME = 'BTC_USDT'
     context.TARGET_HODL_RATIO = 0.8
     context.RESERVE_RATIO = 1.0 - context.TARGET_HODL_RATIO
 
@@ -56,7 +56,7 @@ def handle_data(context, data):
         context.is_buying = False
 
     # Retrieve current asset price from pricing data
-    price = data[context.asset].price
+    price = data.current(context.asset, 'price')
 
     # Check if still buying and could (approximately) afford another purchase
     if context.is_buying and cash > price:
@@ -70,7 +70,7 @@ def handle_data(context, data):
 
     record(
         price=price,
-        volume=data[context.asset].volume,
+        volume=data.current(context.asset, 'volume'),
         cash=cash,
         starting_cash=context.portfolio.starting_cash,
         leverage=context.account.leverage,

catalyst/examples/buy_btc_simple.py

@@ -0,0 +1,29 @@
+'''
+	This is a very simple example referenced in the beginner's tutorial:
+	https://enigmampc.github.io/catalyst/beginner-tutorial.html
+
+	Run this example, by executing the following from your terminal:
+	catalyst run -f buy_btc_simple.py -x bitfinex --start 2016-1-1 --end 2017-9-30 -o buy_btc_simple_out.pickle
+
+	If you want to run this code using another exchange, make sure that 
+	the asset is available on that exchange. For example, if you were to run 
+	it for exchange Poloniex, you would need to edit the following line:
+
+		context.asset = symbol('btc_usdt')     # note 'usdt' instead of 'usd'
+
+	and specify exchange poloniex as follows:
+
+	catalyst run -f buy_btc_simple.py -x poloniex --start 2016-1-1 --end 2017-9-30 -o buy_btc_simple_out.pickle
+
+	To see which assets are available on each exchange, visit:
+	https://www.enigma.co/catalyst/status
+'''
+
+from catalyst.api import order, record, symbol
+
+def initialize(context):
+    context.asset = symbol('btc_usd')
+
+def handle_data(context, data):
+    order(context.asset, 1)
+    record(btc = data.current(context.asset, 'price'))

catalyst/examples/buy_low_sell_high.py

@@ -27,7 +27,7 @@ log = Logger(algo_namespace)
 
 def initialize(context):
     log.info('initializing algo')
-    context.ASSET_NAME = 'XRP_USD'
+    context.ASSET_NAME = 'XRP_USDT'
     context.asset = symbol(context.ASSET_NAME)
 
     context.TARGET_POSITIONS = 5000
@@ -38,6 +38,8 @@ def initialize(context):
     context.retry_update_portfolio = 10
     context.retry_order = 5
 
+    context.swallow_errors = True
+
     context.errors = []
     pass
 
@@ -49,6 +51,7 @@ def _handle_data(context, data):
         bar_count=20,
         frequency='15m'
     )
+
     rsi = talib.RSI(prices.values, timeperiod=14)[-1]
     log.info('got rsi: {}'.format(rsi))
 
@@ -135,11 +138,11 @@ def _handle_data(context, data):
 
 def handle_data(context, data):
     log.info('handling bar {}'.format(data.current_dt))
-    # try:
-    _handle_data(context, data)
-    # except Exception as e:
-    #     log.warn('aborting the bar on error {}'.format(e))
-    #     context.errors.append(e)
+    try:
+        _handle_data(context, data)
+    except Exception as e:
+        log.warn('aborting the bar on error {}'.format(e))
+        context.errors.append(e)
 
     log.info('completed bar {}, total execution errors {}'.format(
         data.current_dt,

catalyst/examples/buy_low_sell_high_live.py

@@ -0,0 +1,168 @@
+import talib
+from logbook import Logger
+
+import pandas as pd
+from catalyst.api import (
+    order,
+    order_target_percent,
+    symbol,
+    record,
+    get_open_orders,
+)
+from catalyst.exchange.stats_utils import get_pretty_stats
+from catalyst.utils.run_algo import run_algorithm
+
+algo_namespace = 'buy_the_dip_live'
+log = Logger('buy low sell high')
+
+
+def initialize(context):
+    log.info('initializing algo')
+    context.ASSET_NAME = 'btc_usdt'
+    context.asset = symbol(context.ASSET_NAME)
+
+    context.TARGET_POSITIONS = 30
+    context.PROFIT_TARGET = 0.1
+    context.SLIPPAGE_ALLOWED = 0.02
+
+    context.retry_check_open_orders = 10
+    context.retry_update_portfolio = 10
+    context.retry_order = 5
+
+    context.errors = []
+    pass
+
+
+def _handle_data(context, data):
+    price = data.current(context.asset, 'price')
+    log.info('got price {price}'.format(price=price))
+
+    prices = data.history(
+        context.asset,
+        fields='price',
+        bar_count=20,
+        frequency='1d'
+    )
+    rsi = talib.RSI(prices.values, timeperiod=14)[-1]
+    log.info('got rsi: {}'.format(rsi))
+
+    # Buying more when RSI is low, this should lower our cost basis
+    if rsi <= 30:
+        buy_increment = 1
+    elif rsi <= 40:
+        buy_increment = 0.5
+    elif rsi <= 70:
+        buy_increment = 0.2
+    else:
+        buy_increment = 0.1
+
+    cash = context.portfolio.cash
+    log.info('base currency available: {cash}'.format(cash=cash))
+
+    record(
+        price=price,
+        rsi=rsi,
+    )
+
+    orders = get_open_orders(context.asset)
+    if orders:
+        log.info('skipping bar until all open orders execute')
+        return
+
+    is_buy = False
+    cost_basis = None
+    if context.asset in context.portfolio.positions:
+        position = context.portfolio.positions[context.asset]
+
+        cost_basis = position.cost_basis
+        log.info(
+            'found {amount} positions with cost basis {cost_basis}'.format(
+                amount=position.amount,
+                cost_basis=cost_basis
+            )
+        )
+
+        if position.amount >= context.TARGET_POSITIONS:
+            log.info('reached positions target: {}'.format(position.amount))
+            return
+
+        if price < cost_basis:
+            is_buy = True
+        elif position.amount > 0 and \
+                        price > cost_basis * (1 + context.PROFIT_TARGET):
+            profit = (price * position.amount) - (cost_basis * position.amount)
+            log.info('closing position, taking profit: {}'.format(profit))
+            order_target_percent(
+                asset=context.asset,
+                target=0,
+                limit_price=price * (1 - context.SLIPPAGE_ALLOWED),
+            )
+        else:
+            log.info('no buy or sell opportunity found')
+    else:
+        is_buy = True
+
+    if is_buy:
+        if buy_increment is None:
+            log.info('the rsi is too high to consider buying {}'.format(rsi))
+            return
+
+        if price * buy_increment > cash:
+            log.info('not enough base currency to consider buying')
+            return
+
+        log.info(
+            'buying position cheaper than cost basis {} < {}'.format(
+                price,
+                cost_basis
+            )
+        )
+        order(
+            asset=context.asset,
+            amount=buy_increment,
+            limit_price=price * (1 + context.SLIPPAGE_ALLOWED)
+        )
+
+
+def handle_data(context, data):
+    log.info('handling bar {}'.format(data.current_dt))
+    # try:
+    _handle_data(context, data)
+    # except Exception as e:
+    #     log.warn('aborting the bar on error {}'.format(e))
+    #     context.errors.append(e)
+
+    log.info('completed bar {}, total execution errors {}'.format(
+        data.current_dt,
+        len(context.errors)
+    ))
+
+    if len(context.errors) > 0:
+        log.info('the errors:\n{}'.format(context.errors))
+
+
+def analyze(context, stats):
+    log.info('the daily stats:\n{}'.format(get_pretty_stats(stats)))
+    pass
+
+
+run_algorithm(
+    capital_base=100000,
+    initialize=initialize,
+    handle_data=handle_data,
+    analyze=analyze,
+    exchange_name='poloniex',
+    start=pd.to_datetime('2017-5-01', utc=True),
+    end=pd.to_datetime('2017-10-16', utc=True),
+    base_currency='usdt',
+    data_frequency='daily'
+)
+# run_algorithm(
+#     initialize=initialize,
+#     handle_data=handle_data,
+#     analyze=analyze,
+#     exchange_name='poloniex',
+#     live=True,
+#     algo_namespace=algo_namespace,
+#     base_currency='btc'
+# )

catalyst/examples/simple_loop.py

@@ -0,0 +1,52 @@
+import talib
+import pandas as pd
+
+from catalyst import run_algorithm
+from catalyst.api import symbol
+
+
+def initialize(context):
+    print('initializing')
+    context.asset = symbol('eth_btc')
+
+
+def handle_data(context, data):
+    print('handling bar: {}'.format(data.current_dt))
+
+    price = data.current(context.asset, 'close')
+    print('got price {price}'.format(price=price))
+
+    try:
+        prices = data.history(
+            context.asset,
+            fields='price',
+            bar_count=16,
+            frequency='5T'
+        )
+        rsi = talib.RSI(prices.values, timeperiod=14)[-1]
+        print('got rsi: {}'.format(rsi))
+    except Exception as e:
+        print(e)
+
+
+run_algorithm(
+    capital_base=250,
+    start=pd.to_datetime('2016-6-1', utc=True),
+    end=pd.to_datetime('2016-12-31', utc=True),
+    data_frequency='daily',
+    initialize=initialize,
+    handle_data=handle_data,
+    analyze=None,
+    exchange_name='bitfinex',
+    algo_namespace='simple_loop',
+    base_currency='btc'
+)
+# run_algorithm(
+#     initialize=initialize,
+#     handle_data=handle_data,
+#     analyze=None,
+#     exchange_name='poloniex',
+#     live=True,
+#     algo_namespace='simple_loop',
+#     base_currency='eth',
+#     live_graph=False

catalyst/exchange/asset_finder_exchange.py

@@ -1,11 +1,12 @@
 from logbook import Logger
 
-log = Logger('AssetFinderExchange')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('AssetFinderExchange', level=LOG_LEVEL)
 
 
 class AssetFinderExchange(object):
-    def __init__(self, exchange):
-        self.exchange = exchange
+    def __init__(self):
         self._asset_cache = {}
 
     @property
@@ -42,12 +43,12 @@ class AssetFinderExchange(object):
         """
         for sid in sids:
             if sid in self._asset_cache:
-                log.info('got asset from cache: {}'.format(sid))
+                log.debug('got asset from cache: {}'.format(sid))
             else:
-                log.info('fetching asset: {}'.format(sid))
+                log.debug('fetching asset: {}'.format(sid))
         return list()
 
-    def lookup_symbol(self, symbol, as_of_date, fuzzy=False):
+    def lookup_symbol(self, symbol, exchange, as_of_date=None, fuzzy=False):
         """Lookup an asset by symbol.
 
         Parameters
@@ -81,11 +82,12 @@ class AssetFinderExchange(object):
             there are multiple candidates for the given ``symbol`` on the
             ``as_of_date``.
         """
-        log.debug('looking up symbol: {}'.format(symbol))
+        log.debug('looking up symbol: {} {}'.format(symbol, exchange.name))
 
-        if symbol in self._asset_cache:
-            return self._asset_cache[symbol]
+        key = ','.join([exchange.name, symbol])
+        if key in self._asset_cache:
+            return self._asset_cache[key]
         else:
-            asset = self.exchange.get_asset(symbol)
-            self._asset_cache[symbol] = asset
+            asset = exchange.get_asset(symbol)
+            self._asset_cache[key] = asset
             return asset

catalyst/exchange/bitfinex/bitfinex.py

@@ -1,4 +1,5 @@
 import base64
+import datetime
 import hashlib
 import hmac
 import json
@@ -13,14 +14,16 @@ import six
 from catalyst.assets._assets import TradingPair
 from logbook import Logger
 
-# from websocket import create_connection
 from catalyst.exchange.exchange import Exchange
+from catalyst.exchange.exchange_bundle import ExchangeBundle
 from catalyst.exchange.exchange_errors import (
     ExchangeRequestError,
     InvalidHistoryFrequencyError,
     InvalidOrderStyle, OrderCancelError)
 from catalyst.exchange.exchange_execution import ExchangeLimitOrder, \
     ExchangeStopLimitOrder, ExchangeStopOrder
+from catalyst.exchange.exchange_utils import get_exchange_symbols_filename, \
+    download_exchange_symbols, get_symbols_string
 from catalyst.finance.order import Order, ORDER_STATUS
 from catalyst.protocol import Account
 
@@ -30,7 +33,9 @@ requests.adapters.DEFAULT_RETRIES = 20
 
 BITFINEX_URL = 'https://api.bitfinex.com'
 
-log = Logger('Bitfinex')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('Bitfinex', level=LOG_LEVEL)
 warning_logger = Logger('AlgoWarning')
 
 
@@ -40,6 +45,7 @@ class Bitfinex(Exchange):
         self.key = key
         self.secret = secret.encode('UTF-8')
         self.name = 'bitfinex'
+        self.color = 'green'
         self.assets = {}
         self.load_assets()
         self.base_currency = base_currency
@@ -47,6 +53,16 @@ class Bitfinex(Exchange):
         self.minute_writer = None
         self.minute_reader = None
 
+        # The candle limit for each request
+        self.num_candles_limit = 1000
+
+        # Max is 90 but playing it safe
+        # https://www.bitfinex.com/posts/188
+        self.max_requests_per_minute = 80
+        self.request_cpt = dict()
+
+        self.bundle = ExchangeBundle(self)
+
     def _request(self, operation, data, version='v1'):
         payload_object = {
             'request': '/{}/{}'.format(version, operation),
@@ -173,6 +189,7 @@ class Bitfinex(Exchange):
     def get_balances(self):
         log.debug('retrieving wallets balances')
         try:
+            self.ask_request()
             response = self._request('balances', None)
             balances = response.json()
         except Exception as e:
@@ -223,7 +240,8 @@ class Bitfinex(Exchange):
         # TODO: fetch account data and keep in cache
         return None
 
-    def get_candles(self, data_frequency, assets, bar_count=None):
+    def get_candles(self, freq, assets, bar_count=None,
+                    start_dt=None, end_dt=None):
         """
         Retrieve OHLVC candles from Bitfinex
 
@@ -237,34 +255,40 @@ class Bitfinex(Exchange):
         '1m', '5m', '15m', '30m', '1h', '3h', '6h', '12h', '1D', '7D', '14D',
          '1M'
         """
+        log.debug(
+            'retrieving {bars} {freq} candles on {exchange} from '
+            '{end_dt} for markets {symbols}, '.format(
+                bars=bar_count,
+                freq=freq,
+                exchange=self.name,
+                end_dt=end_dt,
+                symbols=get_symbols_string(assets)
+            )
+        )
 
-        # TODO: use BcolzMinuteBarReader to read from cache
-        freq_match = re.match(r'([0-9].*)(m|h|d)', data_frequency, re.M | re.I)
+        allowed_frequencies = ['1T', '5T', '15T', '30T', '60T', '180T',
+                               '360T', '720T', '1D', '7D', '14D', '30D']
+        if freq not in allowed_frequencies:
+            raise InvalidHistoryFrequencyError(frequency=freq)
+
+        freq_match = re.match(r'([0-9].*)(T|H|D)', freq, re.M | re.I)
         if freq_match:
             number = int(freq_match.group(1))
             unit = freq_match.group(2)
 
-            if unit == 'd':
-                converted_unit = 'D'
+            if unit == 'T':
+                if number in [60, 180, 360, 720]:
+                    number = number / 60
+                    converted_unit = 'h'
+                else:
+                    converted_unit = 'm'
             else:
                 converted_unit = unit
 
             frequency = '{}{}'.format(number, converted_unit)
-            allowed_frequencies = ['1m', '5m', '15m', '30m', '1h', '3h', '6h',
-                                   '12h', '1D', '7D', '14D', '1M']
 
-            if frequency not in allowed_frequencies:
-                raise InvalidHistoryFrequencyError(
-                    frequency=data_frequency
-                )
-        elif data_frequency == 'minute':
-            frequency = '1m'
-        elif data_frequency == 'daily':
-            frequency = '1D'
         else:
-            raise InvalidHistoryFrequencyError(
-                frequency=data_frequency
-            )
+            raise InvalidHistoryFrequencyError(frequency=freq)
 
         # Making sure that assets are iterable
         asset_list = [assets] if isinstance(assets, TradingPair) else assets
@@ -280,11 +304,27 @@ class Bitfinex(Exchange):
             if bar_count:
                 is_list = True
                 url += '/hist?limit={}'.format(int(bar_count))
+
+                def get_ms(date):
+                    epoch = datetime.datetime.utcfromtimestamp(0)
+                    epoch = epoch.replace(tzinfo=pytz.UTC)
+
+                    return (date - epoch).total_seconds() * 1000.0
+
+                if start_dt is not None:
+                    start_ms = get_ms(start_dt)
+                    url += '&start={0:f}'.format(start_ms)
+
+                if end_dt is not None:
+                    end_ms = get_ms(end_dt)
+                    url += '&end={0:f}'.format(end_ms)
+
             else:
                 is_list = False
                 url += '/last'
 
             try:
+                self.ask_request()
                 response = requests.get(url)
             except Exception as e:
                 raise ExchangeRequestError(error=e)
@@ -298,6 +338,9 @@ class Bitfinex(Exchange):
             candles = response.json()
 
             def ohlc_from_candle(candle):
+                last_traded = pd.Timestamp.utcfromtimestamp(
+                    candle[0] / 1000.0)
+                last_traded = last_traded.replace(tzinfo=pytz.UTC)
                 ohlc = dict(
                     open=np.float64(candle[1]),
                     high=np.float64(candle[3]),
@@ -305,8 +348,7 @@ class Bitfinex(Exchange):
                     close=np.float64(candle[2]),
                     volume=np.float64(candle[5]),
                     price=np.float64(candle[2]),
-                    last_traded=pd.Timestamp.utcfromtimestamp(
-                        candle[0] / 1000.0)
+                    last_traded=last_traded
                 )
                 return ohlc
 
@@ -367,6 +409,7 @@ class Bitfinex(Exchange):
 
         date = pd.Timestamp.utcnow()
         try:
+            self.ask_request()
             response = self._request('order/new', req)
             order_status = response.json()
         except Exception as e:
@@ -408,6 +451,7 @@ class Bitfinex(Exchange):
             orders for this asset.
         """
         try:
+            self.ask_request()
             response = self._request('orders', None)
             order_statuses = response.json()
         except Exception as e:
@@ -419,7 +463,7 @@ class Bitfinex(Exchange):
                     order_statuses['message'])
             )
 
-        orders = list()
+        orders = []
         for order_status in order_statuses:
             order, executed_price = self._create_order(order_status)
             if asset is None or asset == order.sid:
@@ -442,6 +486,7 @@ class Bitfinex(Exchange):
             The order object.
         """
         try:
+            self.ask_request()
             response = self._request(
                 'order/status', {'order_id': int(order_id)})
             order_status = response.json()
@@ -467,6 +512,7 @@ class Bitfinex(Exchange):
             if isinstance(order_param, Order) else order_param
 
         try:
+            self.ask_request()
             response = self._request('order/cancel', {'order_id': order_id})
             status = response.json()
         except Exception as e:
@@ -491,6 +537,7 @@ class Bitfinex(Exchange):
         log.debug('fetching tickers {}'.format(symbols))
 
         try:
+            self.ask_request()
             response = requests.get(
                 '{url}/v2/tickers?symbols={symbols}'.format(
                     url=self.url,
@@ -506,7 +553,10 @@ class Bitfinex(Exchange):
                     response.content)
             )
 
-        tickers = response.json()
+        try:
+            tickers = response.json()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
 
         ticks = dict()
         for index, ticker in enumerate(tickers):
@@ -527,3 +577,124 @@ class Bitfinex(Exchange):
 
         log.debug('got tickers {}'.format(ticks))
         return ticks
+
+    def generate_symbols_json(self, filename=None, source_dates=False):
+        symbol_map = {}
+
+        if not source_dates:
+            fn, r = download_exchange_symbols(self.name)
+            with open(fn) as data_file:
+                cached_symbols = json.load(data_file)
+
+        response = self._request('symbols', None)
+
+        for symbol in response.json():
+            if (source_dates):
+                start_date = self.get_symbol_start_date(symbol)
+            else:
+                try:
+                    start_date = cached_symbols[symbol]['start_date']
+                except KeyError as e:
+                    start_date = time.strftime('%Y-%m-%d')
+
+            try:
+                end_daily = cached_symbols[symbol]['end_daily']
+            except KeyError as e:
+                end_daily = 'N/A'
+
+            try:
+                end_minute = cached_symbols[symbol]['end_minute']
+            except KeyError as e:
+                end_minute = 'N/A'
+
+            symbol_map[symbol] = dict(
+                symbol=symbol[:-3] + '_' + symbol[-3:],
+                start_date=start_date,
+                end_daily=end_daily,
+                end_minute=end_minute,
+            )
+
+        if (filename is None):
+            filename = get_exchange_symbols_filename(self.name)
+
+        with open(filename, 'w') as f:
+            json.dump(symbol_map, f, sort_keys=True, indent=2,
+                      separators=(',', ':'))
+
+    def get_symbol_start_date(self, symbol):
+
+        print(symbol)
+        symbol_v2 = 't' + symbol.upper()
+
+        """
+            For each symbol we retrieve candles with Monhtly resolution
+            We get the first month, and query again with daily resolution
+            around that date, and we get the first date
+        """
+        url = '{url}/v2/candles/trade:1M:{symbol}/hist'.format(
+            url=self.url,
+            symbol=symbol_v2
+        )
+
+        try:
+            self.ask_request()
+            response = requests.get(url)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        """
+            If we don't get any data back for our monthly-resolution query
+            it means that symbol started trading less than a month ago, so
+            arbitrarily set the ref. date to 15 days ago to be safe with
+            +/- 31 days
+        """
+        if (len(response.json())):
+            startmonth = response.json()[-1][0]
+        else:
+            startmonth = int((time.time() - 15 * 24 * 3600) * 1000)
+
+        """
+            Query again with daily resolution setting the start and end around
+            the startmonth we got above. Avoid end dates greater than now: time.time()
+        """
+        url = '{url}/v2/candles/trade:1D:{symbol}/hist?start={start}&end={end}'.format(
+            url=self.url,
+            symbol=symbol_v2,
+            start=startmonth - 3600 * 24 * 31 * 1000,
+            end=min(startmonth + 3600 * 24 * 31 * 1000,
+                    int(time.time() * 1000))
+        )
+
+        try:
+            self.ask_request()
+            response = requests.get(url)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        return time.strftime('%Y-%m-%d',
+                             time.gmtime(int(response.json()[-1][0] / 1000)))
+
+    def get_orderbook(self, asset, order_type='all', limit=100):
+        exchange_symbol = asset.exchange_symbol
+        try:
+            self.ask_request()
+            # TODO: implement limit
+            response = self._request(
+                'book/{}'.format(exchange_symbol), None)
+            data = response.json()
+
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        # TODO: filter by type
+        result = dict()
+        for order_type in data:
+            result[order_type] = []
+
+            for entry in data[order_type]:
+                result[order_type].append(dict(
+                    rate=float(entry['price']),
+                    quantity=float(entry['amount'])
+                ))
+
+        return result

catalyst/exchange/bitfinex/symbols.json

@@ -1,4 +1,17 @@
 {
+  "neobtc": {
+    "symbol": "neo_btc",
+    "start_date": "2017-09-07",
+    "precision": 5
+  },
+  "neousd": {
+    "symbol": "neo_usd",
+    "start_date": "2017-09-07"
+  },
+  "neoeth": {
+    "symbol": "neo_eth",
+    "start_date": "2017-09-07"
+  },
   "btcusd": {
     "symbol": "btc_usd",
     "start_date": "2010-01-01"
@@ -17,19 +30,19 @@
   },
   "ethusd": {
     "symbol": "eth_usd",
-    "start_date": "2010-01-01"
+    "start_date": "2017-01-01"
   },
   "ethbtc": {
     "symbol": "eth_btc",
-    "start_date": "2010-01-01"
+    "start_date": "2017-01-01"
   },
   "etcbtc": {
     "symbol": "etc_btc",
-    "start_date": "2010-01-01"
+    "start_date": "2017-01-01"
   },
   "etcusd": {
     "symbol": "etc_usd",
-    "start_date": "2010-01-01"
+    "start_date": "2017-01-01"
   },
   "rrtusd": {
     "symbol": "rrt_usd",

catalyst/exchange/bittrex/bittrex.py

@@ -1,36 +1,53 @@
 import json
+import time
 
 import pandas as pd
 from catalyst.assets._assets import TradingPair
 from logbook import Logger
 from six.moves import urllib
 
+from catalyst.constants import LOG_LEVEL
 from catalyst.exchange.bittrex.bittrex_api import Bittrex_api
 from catalyst.exchange.exchange import Exchange
+from catalyst.exchange.exchange_bundle import ExchangeBundle
 from catalyst.exchange.exchange_errors import InvalidHistoryFrequencyError, \
     ExchangeRequestError, InvalidOrderStyle, OrderNotFound, OrderCancelError, \
     CreateOrderError
+from catalyst.exchange.exchange_utils import get_exchange_symbols_filename, \
+    download_exchange_symbols, get_symbols_string
 from catalyst.finance.execution import LimitOrder, StopLimitOrder
 from catalyst.finance.order import Order, ORDER_STATUS
 
-log = Logger('Bittrex')
+# TODO: consider using this: https://github.com/mondeja/bittrex_v2
+
+log = Logger('Bittrex', level=LOG_LEVEL)
 
 URL2 = 'https://bittrex.com/Api/v2.0'
 
 
 class Bittrex(Exchange):
     def __init__(self, key, secret, base_currency, portfolio=None):
-        self.api = Bittrex_api(key=key, secret=secret.encode('UTF-8'))
+        self.api = Bittrex_api(key=key, secret=secret)
         self.name = 'bittrex'
+        self.color = 'blue'
         self.base_currency = base_currency
         self._portfolio = portfolio
 
+        self.num_candles_limit = 2000
+
+        # Not sure what the rate limit is but trying to play it safe
+        # https://bitcoin.stackexchange.com/questions/53778/bittrex-api-rate-limit
+        self.max_requests_per_minute = 60
+        self.request_cpt = dict()
+
         self.minute_writer = None
         self.minute_reader = None
 
         self.assets = dict()
         self.load_assets()
 
+        self.bundle = ExchangeBundle(self)
+
     @property
     def account(self):
         pass
@@ -50,42 +67,24 @@ class Bittrex(Exchange):
         """
         return exchange_symbol.lower()
 
-    def fetch_symbol_map(self):
-        """
-        Since Bittrex gives us a complete dictionary of symbols,
-        we can build the symbol map ad-hoc as opposed to maintaining
-        a static file. We must be careful with mapping any unconventional
-        symbol name as appropriate.
-
-        :return symbol_map:
-        """
-        symbol_map = dict()
-
-        markets = self.api.getmarkets()
-        for market in markets:
-            exchange_symbol = market['MarketName']
-            symbol = '{market}_{base}'.format(
-                market=self.sanitize_curency_symbol(market['MarketCurrency']),
-                base=self.sanitize_curency_symbol(market['BaseCurrency'])
-            )
-            symbol_map[exchange_symbol] = dict(
-                symbol=symbol,
-                start_date=pd.to_datetime(market['Created'], utc=True)
-            )
-
-        return symbol_map
-
     def get_balances(self):
+        balances = self.api.getbalances()
         try:
             log.debug('retrieving wallet balances')
-            balances = self.api.getbalances()
+            self.ask_request()
+
         except Exception as e:
             raise ExchangeRequestError(error=e)
 
         std_balances = dict()
-        for balance in balances:
-            currency = balance['Currency'].lower()
-            std_balances[currency] = balance['Available']
+        try:
+            for balance in balances:
+                currency = balance['Currency'].lower()
+                std_balances[currency] = balance['Available']
+
+        except TypeError:
+            raise ExchangeRequestError(error=balances)
+
         return std_balances
 
     def create_order(self, asset, amount, is_buy, style):
@@ -98,6 +97,7 @@ class Bittrex(Exchange):
 
             price = style.get_limit_price(is_buy)
             try:
+                self.ask_request()
                 if is_buy:
                     order_status = self.api.buylimit(exchange_symbol, amount,
                                                      price)
@@ -138,6 +138,7 @@ class Bittrex(Exchange):
     def get_open_orders(self, asset):
         symbol = self.get_symbol(asset)
         try:
+            self.ask_request()
             open_orders = self.api.getopenorders(symbol)
         except Exception as e:
             raise ExchangeRequestError(error=e)
@@ -181,6 +182,7 @@ class Bittrex(Exchange):
     def get_order(self, order_id):
         log.info('retrieving order {}'.format(order_id))
         try:
+            self.ask_request()
             order_status = self.api.getorder(order_id)
         except Exception as e:
             raise ExchangeRequestError(error=e)
@@ -196,6 +198,7 @@ class Bittrex(Exchange):
         log.info('cancelling order {}'.format(order_id))
 
         try:
+            self.ask_request()
             status = self.api.cancel(order_id)
         except Exception as e:
             raise ExchangeRequestError(error=e)
@@ -207,43 +210,59 @@ class Bittrex(Exchange):
                 error=status['message']
             )
 
-    def get_candles(self, data_frequency, assets, bar_count=None):
+    def get_candles(self, freq, assets, bar_count=None,
+                    start_dt=None, end_dt=None):
         """
         Supported Intervals
         -------------------
         day, oneMin, fiveMin, thirtyMin, hour
 
-        :param data_frequency:
+        :param freq:
         :param assets:
         :param bar_count:
+        :param start_dt
+        :param end_dt
         :return:
         """
-        log.info('retrieving candles')
 
-        if data_frequency == 'minute' or data_frequency == '1m':
+        # TODO: this has no effect at the moment
+        if end_dt is None:
+            end_dt = pd.Timestamp.utcnow()
+
+        log.debug(
+            'retrieving {bars} {freq} candles on {exchange} from '
+            '{end_dt} for markets {symbols}, '.format(
+                bars=bar_count,
+                freq=freq,
+                exchange=self.name,
+                end_dt=end_dt,
+                symbols=get_symbols_string(assets)
+            )
+        )
+
+        if freq == '1T':
             frequency = 'oneMin'
-        elif data_frequency == '5m':
+        elif freq == '5T':
             frequency = 'fiveMin'
-        elif data_frequency == '30m':
+        elif freq == '30T':
             frequency = 'thirtyMin'
-        elif data_frequency == '1h':
+        elif freq == '60T':
             frequency = 'hour'
-        elif data_frequency == 'daily' or data_frequency == '1D':
+        elif freq == '1D':
             frequency = 'day'
         else:
-            raise InvalidHistoryFrequencyError(
-                frequency=data_frequency
-            )
+            raise InvalidHistoryFrequencyError(frequency=freq)
 
         # Making sure that assets are iterable
         asset_list = [assets] if isinstance(assets, TradingPair) else assets
-        ohlc_map = dict()
         for asset in asset_list:
+            end = int(time.mktime(end_dt.timetuple()))
             url = '{url}/pub/market/GetTicks?marketName={symbol}' \
-                  '&tickInterval={frequency}&_=1499127220008'.format(
+                  '&tickInterval={frequency}&_={end}'.format(
                 url=URL2,
                 symbol=self.get_symbol(asset),
-                frequency=frequency
+                frequency=frequency,
+                end=end
             )
 
             try:
@@ -271,9 +290,11 @@ class Bittrex(Exchange):
                 return ohlc
 
             ordered_candles = list(reversed(candles))
+            ohlc_map = dict()
             if bar_count is None:
                 ohlc_map[asset] = ohlc_from_candle(ordered_candles[0])
             else:
+                # TODO: optimize
                 ohlc_bars = []
                 for candle in ordered_candles[:bar_count]:
                     ohlc = ohlc_from_candle(candle)
@@ -298,6 +319,7 @@ class Bittrex(Exchange):
         for asset in assets:
             symbol = self.get_symbol(asset)
             try:
+                self.ask_request()
                 ticker = self.api.getticker(symbol)
             except Exception as e:
                 raise ExchangeRequestError(error=e)
@@ -316,3 +338,76 @@ class Bittrex(Exchange):
     def get_account(self):
         log.info('retrieving account data')
         pass
+
+    def generate_symbols_json(self, filename=None):
+        symbol_map = {}
+
+        fn, r = download_exchange_symbols(self.name)
+        with open(fn) as data_file:
+            cached_symbols = json.load(data_file)
+
+        markets = self.api.getmarkets()
+        for market in markets:
+            exchange_symbol = market['MarketName']
+            symbol = '{market}_{base}'.format(
+                market=self.sanitize_curency_symbol(market['MarketCurrency']),
+                base=self.sanitize_curency_symbol(market['BaseCurrency'])
+            )
+
+            try:
+                end_daily = cached_symbols[exchange_symbol]['end_daily']
+            except KeyError as e:
+                end_daily = 'N/A'
+
+            try:
+                end_minute = cached_symbols[exchange_symbol]['end_minute']
+            except KeyError as e:
+                end_minute = 'N/A'
+
+            symbol_map[exchange_symbol] = dict(
+                symbol=symbol,
+                start_date=pd.to_datetime(market['Created'],
+                                          utc=True).strftime("%Y-%m-%d"),
+                end_daily=end_daily,
+                end_minute=end_minute,
+            )
+
+        if (filename is None):
+            filename = get_exchange_symbols_filename(self.name)
+
+        with open(filename, 'w') as f:
+            json.dump(symbol_map, f, sort_keys=True, indent=2,
+                      separators=(',', ':'))
+
+    def get_orderbook(self, asset, order_type='all', limit=100):
+        if order_type == 'all':
+            order_type = 'both'
+        elif order_type == 'bid':
+            order_type = 'buy'
+        elif order_type == 'ask':
+            order_type = 'sell'
+        else:
+            raise ValueError('invalid type')
+
+        exchange_symbol = asset.exchange_symbol
+        data = self.api.getorderbook(
+            market=exchange_symbol,
+            type=order_type,
+            depth=100
+        )
+
+        result = dict()
+        for exchange_type in data:
+            if exchange_type == 'buy':
+                order_type = 'bids'
+            elif exchange_type == 'sell':
+                order_type = 'asks'
+
+            result[order_type] = []
+            for entry in data[exchange_type]:
+                result[order_type].append(dict(
+                    rate=entry['Rate'],
+                    quantity=entry['Quantity']
+                ))
+
+        return result

catalyst/exchange/bittrex/bittrex_api.py

@@ -4,10 +4,10 @@ import time
 import hmac
 import hashlib
 
-from six.moves import urllib
 
 # Workaround for backwards compatibility
 # https://stackoverflow.com/questions/3745771/urllib-request-in-python-2-7
+from six.moves import urllib
 urlopen = urllib.request.urlopen
 
 
@@ -39,7 +39,10 @@ class Bittrex_api(object):
         if method not in self.public:
             url += '&apikey=' + self.key
             url += '&nonce=' + str(int(time.time()))
-            signature = hmac.new(self.secret, url, hashlib.sha512).hexdigest()
+
+            signature = hmac.new(self.secret.encode('utf-8'),
+                                 url.encode('utf-8'),
+                                 hashlib.sha512).hexdigest()
             headers = {'apisign': signature}
         else:
             headers = {}

catalyst/exchange/bittrex/extensions-example.py

@@ -0,0 +1,7 @@
+from catalyst.data.bundles import register
+from catalyst.exchange.exchange_bundle import exchange_bundle
+
+symbols = (
+    'neo_btc',
+)
+register('exchange_bitfinex', exchange_bundle('bitfinex', symbols))

catalyst/exchange/bundle_utils.py

@@ -0,0 +1,316 @@
+import calendar
+import os
+import tarfile
+from datetime import timedelta, datetime, date
+
+import numpy as np
+import pandas as pd
+import pytz
+
+from catalyst.data.bundles.core import download_without_progress
+from catalyst.exchange.exchange_utils import get_exchange_bundles_folder
+
+EXCHANGE_NAMES = ['bitfinex', 'bittrex', 'poloniex']
+API_URL = 'http://data.enigma.co/api/v1'
+
+
+def get_date_from_ms(ms):
+    """
+    The date from the number of miliseconds from the epoch.
+
+    Parameters
+    ----------
+    ms: int
+
+    Returns
+    -------
+    datetime
+
+    """
+    return datetime.fromtimestamp(ms / 1000.0)
+
+
+def get_seconds_from_date(date):
+    """
+    The number of seconds from the epoch.
+
+    Parameters
+    ----------
+    date: datetime
+
+    Returns
+    -------
+    int
+
+    """
+    epoch = datetime.utcfromtimestamp(0)
+    epoch = epoch.replace(tzinfo=pytz.UTC)
+
+    return int((date - epoch).total_seconds())
+
+
+def get_bcolz_chunk(exchange_name, symbol, data_frequency, period):
+    """
+    Download and extract a bcolz bundle.
+
+    Parameters
+    ----------
+    exchange_name: str
+    symbol: str
+    data_frequency: str
+    period: str
+
+    Returns
+    -------
+    str
+        Filename: bitfinex-daily-neo_eth-2017-10.tar.gz
+
+    """
+    root = get_exchange_bundles_folder(exchange_name)
+    name = '{exchange}-{frequency}-{symbol}-{period}'.format(
+        exchange=exchange_name,
+        frequency=data_frequency,
+        symbol=symbol,
+        period=period
+    )
+    path = os.path.join(root, name)
+
+    if not os.path.isdir(path):
+        url = 'https://s3.amazonaws.com/enigmaco/catalyst-bundles/' \
+              'exchange-{exchange}/{name}.tar.gz'.format(
+            exchange=exchange_name,
+            name=name
+        )
+
+        bytes = download_without_progress(url)
+        with tarfile.open('r', fileobj=bytes) as tar:
+            tar.extractall(path)
+
+    return path
+
+
+def get_delta(periods, data_frequency):
+    """
+    Get a time delta based on the specified data frequency.
+
+    Parameters
+    ----------
+    periods: int
+    data_frequency: str
+
+    Returns
+    -------
+    timedelta
+
+    """
+    return timedelta(minutes=periods) \
+        if data_frequency == 'minute' else timedelta(days=periods)
+
+
+def get_periods_range(start_dt, end_dt, freq):
+    """
+    Get a date range for the specified parameters.
+
+    Parameters
+    ----------
+    start_dt: datetime
+    end_dt: datetime
+    freq: str
+
+    Returns
+    -------
+    DateTimeIndex
+
+    """
+    if freq == 'minute':
+        freq = 'T'
+
+    elif freq == 'daily':
+        freq = 'D'
+
+    return pd.date_range(start_dt, end_dt, freq=freq)
+
+
+def get_periods(start_dt, end_dt, freq):
+    """
+    The number of periods in the specified range.
+
+    Parameters
+    ----------
+    start_dt: datetime
+    end_dt: datetime
+    freq: str
+
+    Returns
+    -------
+    int
+
+    """
+    return len(get_periods_range(start_dt, end_dt, freq))
+
+
+def get_start_dt(end_dt, bar_count, data_frequency):
+    """
+    The start date based on specified end date and data frequency.
+
+    Parameters
+    ----------
+    end_dt: datetime
+    bar_count: int
+    data_frequency: str
+
+    Returns
+    -------
+    datetime
+
+    """
+    periods = bar_count
+    if periods > 1:
+        delta = get_delta(periods, data_frequency)
+        start_dt = end_dt - delta
+    else:
+        start_dt = end_dt
+
+    return start_dt
+
+
+def get_period_label(dt, data_frequency):
+    """
+    The period label for the specified date and frequency.
+
+    Parameters
+    ----------
+    dt: datetime
+    data_frequency: str
+
+    Returns
+    -------
+    str
+
+    """
+    return '{}-{:02d}'.format(dt.year, dt.month) if data_frequency == 'minute' \
+        else '{}'.format(dt.year)
+
+
+def get_month_start_end(dt, first_day=None, last_day=None):
+    """
+    The first and last day of the month for the specified date.
+
+    Parameters
+    ----------
+    dt: datetime
+    first_day: datetime
+    last_day: datetime
+
+    Returns
+    -------
+    datetime, datetime
+
+    """
+    month_range = calendar.monthrange(dt.year, dt.month)
+
+    if first_day:
+        month_start = first_day
+    else:
+        month_start = pd.to_datetime(datetime(
+            dt.year, dt.month, 1, 0, 0, 0, 0
+        ), utc=True)
+
+    if last_day:
+        month_end = last_day
+    else:
+        month_end = pd.to_datetime(datetime(
+            dt.year, dt.month, month_range[1], 23, 59, 0, 0
+        ), utc=True)
+
+        if month_end > pd.Timestamp.utcnow():
+            month_end = pd.Timestamp.utcnow().floor('1D')
+
+    return month_start, month_end
+
+
+def get_year_start_end(dt, first_day=None, last_day=None):
+    """
+    The first and last day of the year for the specified date.
+
+    Parameters
+    ----------
+
+    dt: datetime
+    first_day: datetime
+    last_day: datetime
+
+    Returns
+    -------
+    datetime, datetime
+
+    """
+    year_start = first_day if first_day \
+        else pd.to_datetime(date(dt.year, 1, 1), utc=True)
+    year_end = last_day if last_day \
+        else pd.to_datetime(date(dt.year, 12, 31), utc=True)
+
+    if year_end > pd.Timestamp.utcnow():
+        year_end = pd.Timestamp.utcnow().floor('1D')
+
+    return year_start, year_end
+
+
+def get_df_from_arrays(arrays, periods):
+    """
+    A DataFrame from the specified OHCLV arrays.
+
+    Parameters
+    ----------
+    arrays: Object
+    periods: DateTimeIndex
+
+    Returns
+    -------
+    DataFrame
+
+    """
+    ohlcv = dict()
+    for index, field in enumerate(
+            ['open', 'high', 'low', 'close', 'volume']):
+        ohlcv[field] = arrays[index].flatten()
+
+    df = pd.DataFrame(
+        data=ohlcv,
+        index=periods
+    )
+    return df
+
+
+def range_in_bundle(asset, start_dt, end_dt, reader):
+    """
+    Evaluate whether price data of an asset is included has been ingested in
+    the exchange bundle for the given date range.
+
+    Parameters
+    ----------
+    asset: TradingPair
+    start_dt: datetime
+    end_dt: datetime
+    reader: BcolzBarMinuteReader
+
+    Returns
+    -------
+    bool
+
+    """
+    has_data = True
+    dates = [start_dt, end_dt]
+
+    while dates and has_data:
+        try:
+            dt = dates.pop(0)
+            close = reader.get_value(asset.sid, dt, 'close')
+
+            if np.isnan(close):
+                has_data = False
+
+        except Exception as e:
+            has_data = False
+
+    return has_data

catalyst/exchange/data_portal_exchange.py

@@ -1,121 +0,0 @@
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-from time import sleep
-
-from logbook import Logger
-
-from catalyst.data.data_portal import DataPortal
-from catalyst.exchange.exchange_errors import (
-    ExchangeRequestError,
-    ExchangeBarDataError
-)
-
-log = Logger('DataPortalExchange')
-
-
-class DataPortalExchange(DataPortal):
-    def __init__(self, exchange, *args, **kwargs):
-        self.exchange = exchange
-
-        # TODO: put somewhere accessible by each algo
-        self.retry_get_history_window = 5
-        self.retry_get_spot_value = 5
-        self.retry_delay = 5
-
-        super(DataPortalExchange, self).__init__(*args, **kwargs)
-
-    def _get_history_window(self,
-                            assets,
-                            end_dt,
-                            bar_count,
-                            frequency,
-                            field,
-                            data_frequency,
-                            ffill=True,
-                            attempt_index=0):
-        try:
-            return self.exchange.get_history_window(
-                assets,
-                end_dt,
-                bar_count,
-                frequency,
-                field,
-                data_frequency,
-                ffill)
-        except ExchangeRequestError as e:
-            log.warn(
-                'get history attempt {}: {}'.format(attempt_index, e)
-            )
-            if attempt_index < self.retry_get_history_window:
-                sleep(self.retry_delay)
-                return self._get_history_window(assets,
-                                                end_dt,
-                                                bar_count,
-                                                frequency,
-                                                field,
-                                                data_frequency,
-                                                ffill,
-                                                attempt_index + 1)
-            else:
-                raise ExchangeBarDataError(
-                    data_type='history',
-                    attempts=attempt_index,
-                    error=e
-                )
-
-    def get_history_window(self,
-                           assets,
-                           end_dt,
-                           bar_count,
-                           frequency,
-                           field,
-                           data_frequency,
-                           ffill=True):
-        return self._get_history_window(assets,
-                                        end_dt,
-                                        bar_count,
-                                        frequency,
-                                        field,
-                                        data_frequency,
-                                        ffill)
-
-    def _get_spot_value(self, assets, field, dt, data_frequency,
-                        attempt_index=0):
-        try:
-            return self.exchange.get_spot_value(assets, field, dt,
-                                                data_frequency)
-        except ExchangeRequestError as e:
-            log.warn(
-                'get spot value attempt {}: {}'.format(attempt_index, e)
-            )
-            if attempt_index < self.retry_get_spot_value:
-                sleep(self.retry_delay)
-                return self._get_spot_value(assets, field, dt, data_frequency,
-                                            attempt_index + 1)
-            else:
-                raise ExchangeBarDataError(
-                    data_type='spot',
-                    attempts=attempt_index,
-                    error=e
-                )
-
-    def get_spot_value(self, assets, field, dt, data_frequency):
-        return self._get_spot_value(assets, field, dt, data_frequency)
-
-    def get_adjusted_value(self, asset, field, dt,
-                           perspective_dt,
-                           data_frequency,
-                           spot_value=None):
-        # TODO: does this pertain to cryptocurrencies?
-        raise NotImplementedError("get_adjusted_value is not implemented yet!")

catalyst/exchange/exchange.py

@@ -1,7 +1,6 @@
 import abc
-import collections
-import random
 from abc import ABCMeta, abstractmethod, abstractproperty
+from datetime import timedelta
 from time import sleep
 
 import numpy as np
@@ -9,20 +8,25 @@ import pandas as pd
 from catalyst.assets._assets import TradingPair
 from logbook import Logger
 
+from catalyst.constants import LOG_LEVEL
 from catalyst.data.data_portal import BASE_FIELDS
-from catalyst.errors import (
-    SymbolNotFound,
-)
+from catalyst.exchange.bundle_utils import get_start_dt, \
+    get_delta, get_periods, get_periods_range
+from catalyst.exchange.exchange_bundle import ExchangeBundle
 from catalyst.exchange.exchange_errors import MismatchingBaseCurrencies, \
-    InvalidOrderStyle, BaseCurrencyNotFoundError
+    InvalidOrderStyle, BaseCurrencyNotFoundError, SymbolNotFoundOnExchange, \
+    PricingDataNotLoadedError, \
+    NoDataAvailableOnExchange
 from catalyst.exchange.exchange_execution import ExchangeStopLimitOrder, \
     ExchangeLimitOrder, ExchangeStopOrder
 from catalyst.exchange.exchange_portfolio import ExchangePortfolio
-from catalyst.exchange.exchange_utils import get_exchange_symbols
+from catalyst.exchange.exchange_utils import get_exchange_symbols, \
+    get_frequency, resample_history_df
 from catalyst.finance.order import ORDER_STATUS
 from catalyst.finance.transaction import Transaction
+from catalyst.utils.deprecate import deprecated
 
-log = Logger('Exchange')
+log = Logger('Exchange', level=LOG_LEVEL)
 
 
 class Exchange:
@@ -30,13 +34,17 @@ class Exchange:
 
     def __init__(self):
         self.name = None
-        self.trading_pairs = None
         self.assets = {}
         self._portfolio = None
         self.minute_writer = None
         self.minute_reader = None
         self.base_currency = None
 
+        self.num_candles_limit = None
+        self.max_requests_per_minute = None
+        self.request_cpt = None
+        self.bundle = ExchangeBundle(self)
+
     @property
     def positions(self):
         return self.portfolio.positions
@@ -44,9 +52,11 @@ class Exchange:
     @property
     def portfolio(self):
         """
-        Return the Portfolio
+        The exchange portfolio
 
-        :return:
+        Returns
+        -------
+        ExchangePortfolio
         """
         if self._portfolio is None:
             self._portfolio = ExchangePortfolio(
@@ -64,12 +74,74 @@ class Exchange:
     def time_skew(self):
         pass
 
+    def is_open(self, dt):
+        """
+        Is the exchange open
+
+        Parameters
+        ----------
+        dt: Timestamp
+
+        Returns
+        -------
+        bool
+
+        """
+        # TODO: implement for each exchange.
+        return True
+
+    def ask_request(self):
+        """
+        Asks permission to issue a request to the exchange.
+        The primary purpose is to avoid hitting rate limits.
+
+        The application will pause if the maximum requests per minute
+        permitted by the exchange is exceeded.
+
+        Returns
+        -------
+        bool
+
+        """
+        now = pd.Timestamp.utcnow()
+        if not self.request_cpt:
+            self.request_cpt = dict()
+            self.request_cpt[now] = 0
+            return True
+
+        cpt_date = list(self.request_cpt.keys())[0]
+        cpt = self.request_cpt[cpt_date]
+
+        if now > cpt_date + timedelta(minutes=1):
+            self.request_cpt = dict()
+            self.request_cpt[now] = 0
+            return True
+
+        if cpt >= self.max_requests_per_minute:
+            delta = now - cpt_date
+
+            sleep_period = 60 - delta.total_seconds()
+            sleep(sleep_period)
+
+            now = pd.Timestamp.utcnow()
+            self.request_cpt = dict()
+            self.request_cpt[now] = 0
+            return True
+        else:
+            self.request_cpt[cpt_date] += 1
+
     def get_symbol(self, asset):
         """
-        Get the exchange specific symbol of the given asset.
+        The the exchange specific symbol of the specified market.
+
+        Parameters
+        ----------
+        asset: TradingPair
+
+        Returns
+        -------
+        str
 
-        :param asset: Asset
-        :return: symbol: str
         """
         symbol = None
 
@@ -79,7 +151,7 @@ class Exchange:
 
         if not symbol:
             raise ValueError('Currency %s not supported by exchange %s' %
-                             (asset['symbol'], self.name))
+                             (asset['symbol'], self.name.title()))
 
         return symbol
 
@@ -87,21 +159,58 @@ class Exchange:
         """
         Get a list of symbols corresponding to each given asset.
 
-        :param assets: Asset[]
-        :return:
+        Parameters
+        ----------
+        assets: list[TradingPair]
+
+        Returns
+        -------
+        list[str]
+
         """
         symbols = []
-
         for asset in assets:
             symbols.append(self.get_symbol(asset))
 
         return symbols
 
+    def get_assets(self, symbols=None):
+        """
+        The list of markets for the specified symbols.
+
+        Parameters
+        ----------
+        symbols: list[str]
+
+        Returns
+        -------
+        list[TradingPair]
+
+        """
+        assets = []
+
+        if symbols is not None:
+            for symbol in symbols:
+                asset = self.get_asset(symbol)
+                assets.append(asset)
+        else:
+            for key in self.assets:
+                assets.append(self.assets[key])
+
+        return assets
+
     def get_asset(self, symbol):
         """
-        Find an Asset on the current exchange based on its Catalyst symbol
-        :param symbol: the [target]_[base] currency pair symbol
-        :return: Asset
+        The market for the specified symbol.
+
+        Parameters
+        ----------
+        symbol: str
+
+        Returns
+        -------
+        TradingPair
+
         """
         asset = None
 
@@ -110,7 +219,15 @@ class Exchange:
                 asset = self.assets[key]
 
         if not asset:
-            raise SymbolNotFound(symbol=symbol)
+            supported_symbols = [
+                pair.symbol for pair in list(self.assets.values())
+            ]
+
+            raise SymbolNotFoundOnExchange(
+                symbol=symbol,
+                exchange=self.name.title(),
+                supported_symbols=supported_symbols
+            )
 
         return asset
 
@@ -124,7 +241,6 @@ class Exchange:
         currency pair symbol. The universal symbol is contained in the
         'symbol' attribute of each asset.
 
-
         Notes
         -----
         The sid of each asset is calculated based on a numeric hash of the
@@ -133,8 +249,8 @@ class Exchange:
 
         This method can be overridden if an exchange offers equivalent data
         via its api.
-        """
 
+        """
         symbol_map = self.fetch_symbol_map()
         for exchange_symbol in symbol_map:
             asset = symbol_map[exchange_symbol]
@@ -159,13 +275,32 @@ class Exchange:
             else:
                 asset_name = None
 
+            if 'min_trade_size' in asset:
+                min_trade_size = asset['min_trade_size']
+            else:
+                min_trade_size = 0.0000001
+
+            if 'end_daily' in asset and asset['end_daily'] != 'N/A':
+                end_daily = pd.to_datetime(asset['end_daily'], utc=True)
+            else:
+                end_daily = None
+
+            if 'end_minute' in asset and asset['end_minute'] != 'N/A':
+                end_minute = pd.to_datetime(asset['end_minute'], utc=True)
+            else:
+                end_minute = None
+
             trading_pair = TradingPair(
                 symbol=asset['symbol'],
                 exchange=self.name,
                 start_date=start_date,
                 end_date=end_date,
                 leverage=leverage,
-                asset_name=asset_name
+                asset_name=asset_name,
+                min_trade_size=min_trade_size,
+                end_daily=end_daily,
+                end_minute=end_minute,
+                exchange_symbol=exchange_symbol
             )
 
             self.assets[exchange_symbol] = trading_pair
@@ -176,8 +311,10 @@ class Exchange:
         For each executed order found, create a transaction and apply to the
         Portfolio.
 
-        :return:
-        transactions: Transaction[]
+        Returns
+        -------
+        list[Transaction]
+
         """
         transactions = list()
         if self.portfolio.open_orders:
@@ -247,35 +384,37 @@ class Exchange:
          '1D', '7D', '14D', '1M'
         """
         if field not in BASE_FIELDS:
-            raise KeyError('Invalid column: ' + str(field))
+            raise KeyError('Invalid column: {}'.format(field))
 
-        if isinstance(assets, collections.Iterable):
-            values = list()
-            for asset in assets:
-                value = self.get_single_spot_value(
-                    asset, field, data_frequency)
-                values.append(value)
+        values = []
+        for asset in assets:
+            value = self.get_single_spot_value(asset, field, data_frequency)
+            values.append(value)
 
-            return values
-        else:
-            return self.get_single_spot_value(
-                assets, field, data_frequency)
+        return values
 
     def get_single_spot_value(self, asset, field, data_frequency):
         """
         Similar to 'get_spot_value' but for a single asset
 
-        Note
-        ----
+        Notes
+        -----
         We're writing each minute bar to disk using zipline's machinery.
         This is especially useful when running multiple algorithms
         concurrently. By using local data when possible, we try to reaching
         request limits on exchanges.
 
-        :param asset:
-        :param field:
-        :param data_frequency:
-        :return value: The spot value of the given asset / field
+        Parameters
+        ----------
+        asset: TradingPair
+        field: str
+        data_frequency: str
+
+        Returns
+        -------
+        float
+            The spot value of the given asset / field
+
         """
         log.debug(
             'fetching spot value {field} for symbol {symbol}'.format(
@@ -284,65 +423,60 @@ class Exchange:
             )
         )
 
-        if field == 'price':
-            field = 'close'
+        freq = '1T' if data_frequency == 'minute' else '1D'
+        ohlc = self.get_candles(freq, asset)
+        if field not in ohlc:
+            raise KeyError('Invalid column: %s' % field)
 
-        # Don't use a timezone here
-        dt = pd.Timestamp.utcnow().floor('1 min')
-        value = None
-        if self.minute_reader is not None:
-            try:
-                # Slight delay to minimize the chances that multiple algos
-                # might try to hit the cache at the exact same time.
-                sleep_time = random.uniform(0.5, 0.8)
-                sleep(sleep_time)
-                # TODO: This does not always! Why is that? Open an issue with zipline.
-                # See: https://github.com/zipline-live/zipline/issues/26
-                value = self.minute_reader.get_value(
-                    sid=asset.sid,
-                    dt=dt,
-                    field=field
-                )
-            except Exception as e:
-                log.warn('minute data not found: {}'.format(e))
-
-        if value is None or np.isnan(value):
-            ohlc = self.get_candles(data_frequency, asset)
-            if field not in ohlc:
-                raise KeyError('Invalid column: %s' % field)
-
-            if self.minute_writer is not None:
-                df = pd.DataFrame(
-                    [ohlc],
-                    index=pd.DatetimeIndex([dt]),
-                    columns=['open', 'high', 'low', 'close', 'volume']
-                )
-
-                try:
-                    self.minute_writer.write_sid(
-                        sid=asset.sid,
-                        df=df
-                    )
-                    log.debug('wrote minute data: {}'.format(dt))
-                except Exception as e:
-                    log.warn(
-                        'unable to write minute data: {} {}'.format(dt, e))
-
-            value = ohlc[field]
-            log.debug('got spot value: {}'.format(value))
-        else:
-            log.debug('got spot value from cache: {}'.format(value))
+        value = ohlc[field]
+        log.debug('got spot value: {}'.format(value))
 
         return value
 
-    def get_history_window(self,
-                           assets,
-                           end_dt,
-                           bar_count,
-                           frequency,
-                           field,
-                           data_frequency,
-                           ffill=True):
+    def get_series_from_candles(self, candles, start_dt, end_dt,
+                                data_frequency, field, previous_value=None):
+        """
+        Get a series of field data for the specified candles.
+
+        Parameters
+        ----------
+        candles: list[dict[str, float]]
+        start_dt: datetime
+        end_dt: datetime
+        data_frequency: str
+        field: str
+        previous_value: float
+
+        Returns
+        -------
+        Series
+
+        """
+        dates = [candle['last_traded'] for candle in candles]
+        values = [candle[field] for candle in candles]
+        series = pd.Series(values, index=dates)
+
+        periods = get_periods_range(
+            start_dt, end_dt, data_frequency
+        )
+        # TODO: ensure that this working as expected, if not use fillna
+        series = series.reindex(
+            periods,
+            method='ffill',
+            fill_value=previous_value,
+        )
+
+        return series
+
+    @deprecated
+    def get_history_window_direct(self,
+                                  assets,
+                                  end_dt,
+                                  bar_count,
+                                  frequency,
+                                  field,
+                                  data_frequency=None,
+                                  ffill=True):
 
         """
         Public API method that returns a dataframe containing the requested
@@ -350,10 +484,11 @@ class Exchange:
 
         Parameters
         ----------
-        assets : list of catalyst.data.Asset objects
+        assets : list[TradingPair]
             The assets whose data is desired.
 
-        end_dt: not applicable to cryptocurrencies
+        end_dt: datetime
+            The date of the last bar
 
         bar_count: int
             The number of bars desired.
@@ -375,26 +510,139 @@ class Exchange:
 
         Returns
         -------
-        A dataframe containing the requested data.
-        """
+        DataFrame
+            A dataframe containing the requested data.
 
+        """
+        start_dt = get_start_dt(end_dt, bar_count, data_frequency)
+
+        # The get_history method supports multiple asset
         candles = self.get_candles(
             data_frequency=frequency,
             assets=assets,
             bar_count=bar_count,
+            start_dt=start_dt,
+            end_dt=end_dt
+        )
+        candle_series = self.get_series_from_candles(
+            candles=candles,
+            start_dt=start_dt,
+            end_dt=end_dt,
+            data_frequency=frequency,
+            field=field,
         )
 
-        series = dict()
+        df = pd.DataFrame(candle_series)
+        return df
+
+    def get_history_window(self,
+                           assets,
+                           end_dt,
+                           bar_count,
+                           frequency,
+                           field,
+                           data_frequency=None,
+                           ffill=True):
+
+        """
+        Public API method that returns a dataframe containing the requested
+        history window.  Data is fully adjusted.
+
+        Parameters
+        ----------
+        assets : list[TradingPair]
+            The assets whose data is desired.
+
+        end_dt: datetime
+            The date of the last bar.
+
+        bar_count: int
+            The number of bars desired.
+
+        frequency: string
+            "1d" or "1m"
+
+        field: string
+            The desired field of the asset.
+
+        data_frequency: string
+            The frequency of the data to query; i.e. whether the data is
+            'daily' or 'minute' bars.
+
+        # TODO: fill how?
+        ffill: boolean
+            Forward-fill missing values. Only has effect if field
+            is 'price'.
+
+        Returns
+        -------
+        DataFrame
+            A dataframe containing the requested data.
+
+        """
+        freq, candle_size, unit, data_frequency = get_frequency(
+            frequency, data_frequency
+        )
+        adj_bar_count = candle_size * bar_count
+        try:
+            series = self.bundle.get_history_window_series_and_load(
+                assets=assets,
+                end_dt=end_dt,
+                bar_count=adj_bar_count,
+                field=field,
+                data_frequency=data_frequency
+            )
+        except (PricingDataNotLoadedError, NoDataAvailableOnExchange):
+            series = dict()
+
         for asset in assets:
-            asset_candles = candles[asset]
+            if asset not in series or series[asset].index[-1] < end_dt:
+                # Adding bars too recent to be contained in the consolidated
+                # exchanges bundles. We go directly against the exchange
+                # to retrieve the candles.
+                start_dt = get_start_dt(end_dt, adj_bar_count, data_frequency)
+                trailing_dt = \
+                    series[asset].index[-1] + get_delta(1, data_frequency) \
+                        if asset in series else start_dt
 
-            values = map(lambda candle: candle[field], asset_candles)
-            dates = map(lambda candle: candle['last_traded'], asset_candles)
+                # The get_history method supports multiple asset
+                # Use the original frequency to let each api optimize
+                # the size of result sets
+                trailing_bar_count = get_periods(
+                    trailing_dt, end_dt, freq
+                )
+                candles = self.get_candles(
+                    freq=freq,
+                    assets=asset,
+                    bar_count=trailing_bar_count,
+                    start_dt=start_dt,
+                    end_dt=end_dt
+                )
 
-            value_series = pd.Series(values, index=dates)
-            series[asset] = value_series
+                last_value = series[asset].iloc(0) if asset in series \
+                    else np.nan
+
+                # Create a series with the common data_frequency, ffill
+                # missing values
+                candle_series = self.get_series_from_candles(
+                    candles=candles,
+                    start_dt=trailing_dt,
+                    end_dt=end_dt,
+                    data_frequency=data_frequency,
+                    field=field,
+                    previous_value=last_value
+                )
+
+                if asset in series:
+                    series[asset].append(candle_series)
+
+                else:
+                    series[asset] = candle_series
+
+        df = resample_history_df(pd.DataFrame(series), freq, field)
+        # TODO: consider this more carefully
+        df.dropna(inplace=True)
 
-        df = pd.concat(series)
         return df
 
     def synchronize_portfolio(self):
@@ -402,7 +650,6 @@ class Exchange:
         Update the portfolio cash and position balances based on the
         latest ticker prices.
 
-        :return:
         """
         log.debug('synchronizing portfolio with exchange {}'.format(self.name))
         balances = self.get_balances()
@@ -413,7 +660,7 @@ class Exchange:
         if base_position_available is None:
             raise BaseCurrencyNotFoundError(
                 base_currency=self.base_currency,
-                exchange=self.name
+                exchange=self.name.title()
             )
 
         portfolio = self._portfolio
@@ -424,7 +671,7 @@ class Exchange:
             portfolio.starting_cash = portfolio.cash
 
         if portfolio.positions:
-            assets = portfolio.positions.keys()
+            assets = list(portfolio.positions.keys())
             tickers = self.tickers(assets)
 
             portfolio.positions_value = 0.0
@@ -440,34 +687,26 @@ class Exchange:
                 portfolio.portfolio_value = \
                     portfolio.positions_value + portfolio.cash
 
-    @abstractmethod
-    def get_balances(self):
-        """
-        Retrieve wallet balances for the exchange
-        :return balances: A dict of currency => available balance
-        """
-        pass
-
-    @abstractmethod
-    def create_order(self, asset, amount, is_buy, style):
-        pass
-
     def order(self, asset, amount, limit_price=None, stop_price=None,
               style=None):
         """Place an order.
 
         Parameters
         ----------
-        asset : Asset
+        asset : TradingPair
             The asset that this order is for.
+
         amount : int
             The amount of shares to order. If ``amount`` is positive, this is
             the number of shares to buy or cover. If ``amount`` is negative,
             this is the number of shares to sell or short.
+
         limit_price : float, optional
             The limit price for the order.
+
         stop_price : float, optional
             The stop price for the order.
+
         style : ExecutionStyle, optional
             The execution style for the order.
 
@@ -492,6 +731,7 @@ class Exchange:
         :class:`catalyst.finance.execution.ExecutionStyle`
         :func:`catalyst.api.order_value`
         :func:`catalyst.api.order_percent`
+
         """
         if amount == 0:
             log.warn('skipping order amount of 0')
@@ -515,7 +755,7 @@ class Exchange:
             style = ExchangeStopOrder(stop_price, exchange=self.name)
 
         elif style is not None:
-            raise InvalidOrderStyle(exchange=self.name,
+            raise InvalidOrderStyle(exchange=self.name.title(),
                                     style=style.__class__.__name__)
         else:
             raise ValueError('Incomplete order data.')
@@ -537,6 +777,46 @@ class Exchange:
         else:
             return None
 
+    # The methods below must be implemented for each exchange.
+    @abstractmethod
+    def get_balances(self):
+        """
+        Retrieve wallet balances for the exchange.
+
+        Returns
+        -------
+        dict[TradingPair, float]
+
+        """
+        pass
+
+    @abstractmethod
+    def create_order(self, asset, amount, is_buy, style):
+        """
+        Place an order on the exchange.
+
+        Parameters
+        ----------
+        asset: TradingPair
+            The target market.
+
+        amount: float
+            The amount of shares to order. If ``amount`` is positive, this is
+            the number of shares to buy or cover. If ``amount`` is negative,
+            this is the number of shares to sell or short.
+
+        is_buy: bool
+            Is it a buy order?
+
+        style: ExecutionStyle
+
+        Returns
+        -------
+        Order
+
+        """
+        pass
+
     @abstractmethod
     def get_open_orders(self, asset):
         """Retrieve all of the current open orders.
@@ -588,16 +868,43 @@ class Exchange:
         pass
 
     @abstractmethod
-    def get_candles(self, data_frequency, assets, bar_count=None):
+    def get_candles(self, freq, assets, bar_count=None,
+                    start_dt=None, end_dt=None):
         """
         Retrieve OHLCV candles for the given assets
 
-        :param data_frequency:
-        :param assets:
-        :param end_dt:
-        :param bar_count:
-        :param limit:
-        :return:
+        Parameters
+        ----------
+        freq: str
+            The frequency alias per convention:
+            http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases
+
+        assets: list[TradingPair]
+            The targeted assets.
+
+        bar_count: int
+            The number of bar desired. (default 1)
+
+        end_dt: datetime, optional
+            The last bar date.
+
+        start_dt: datetime, optional
+            The first bar date.
+
+        Returns
+        -------
+        dict[TradingPair, dict[str, Object]]
+            A dictionary of OHLCV candles. Each TradingPair instance is
+            mapped to a list of dictionaries with this structure:
+                open: float
+                high: float
+                low: float
+                close: float
+                volume: float
+                last_traded: datetime
+
+            See definition here:
+                http://www.investopedia.com/terms/o/ohlcchart.asp
         """
         pass
 
@@ -606,8 +913,14 @@ class Exchange:
         """
         Retrieve current tick data for the given assets
 
-        :param assets:
-        :return:
+        Parameters
+        ----------
+        assets: list[TradingPair]
+
+        Returns
+        -------
+        list[dict[str, float]
+
         """
         pass
 
@@ -615,6 +928,23 @@ class Exchange:
     def get_account(self):
         """
         Retrieve the account parameters.
-        :return:
+        """
+        pass
+
+    @abc.abstractmethod
+    def get_orderbook(self, asset, order_type, limit):
+        """
+        Retrieve the the orderbook for the given trading pair.
+
+        Parameters
+        ----------
+        asset: TradingPair
+        order_type: str
+            The type of orders: bid, ask or all
+        limit: int
+
+        Returns
+        -------
+        list[dict[str, float]
         """
         pass

catalyst/exchange/exchange_algorithm.py

@@ -11,43 +11,51 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import os
+import pickle
 import signal
 import sys
-import pickle
+from collections import deque
 from datetime import timedelta
-from time import sleep
 from os import listdir
 from os.path import isfile, join
-from collections import deque
-import numpy as np
+from time import sleep
 
 import logbook
 import pandas as pd
+from catalyst.assets._assets import TradingPair
 
 import catalyst.protocol as zp
 from catalyst.algorithm import TradingAlgorithm
+from catalyst.constants import LOG_LEVEL
 from catalyst.data.minute_bars import BcolzMinuteBarWriter, \
     BcolzMinuteBarReader
 from catalyst.errors import OrderInBeforeTradingStart
-from catalyst.exchange.simple_clock import SimpleClock
-from catalyst.exchange.live_graph_clock import LiveGraphClock
+from catalyst.exchange.exchange_blotter import ExchangeBlotter
 from catalyst.exchange.exchange_errors import (
     ExchangeRequestError,
     ExchangePortfolioDataError,
-    ExchangeTransactionError
-)
+    ExchangeTransactionError,
+    OrphanOrderError)
+from catalyst.exchange.exchange_execution import ExchangeStopLimitOrder, \
+    ExchangeLimitOrder, ExchangeStopOrder
 from catalyst.exchange.exchange_utils import get_exchange_minute_writer_root, \
     save_algo_object, get_algo_object, get_algo_folder, get_algo_df, \
     save_algo_df
+from catalyst.exchange.live_graph_clock import LiveGraphClock
+from catalyst.exchange.simple_clock import SimpleClock
 from catalyst.exchange.stats_utils import get_pretty_stats
+from catalyst.finance.execution import MarketOrder
 from catalyst.finance.performance.period import calc_period_stats
 from catalyst.gens.tradesimulation import AlgorithmSimulator
 from catalyst.utils.api_support import (
     api_method,
     disallowed_in_before_trading_start)
-from catalyst.utils.input_validation import error_keywords
+from catalyst.utils.input_validation import error_keywords, ensure_upper_case, \
+    expect_types
+from catalyst.utils.math_utils import round_nearest
+from catalyst.utils.preprocess import preprocess
 
-log = logbook.Logger("ExchangeTradingAlgorithm")
+log = logbook.Logger('exchange_algorithm', level=LOG_LEVEL)
 
 
 class ExchangeAlgorithmExecutor(AlgorithmSimulator):
@@ -55,253 +63,77 @@ class ExchangeAlgorithmExecutor(AlgorithmSimulator):
         super(self.__class__, self).__init__(*args, **kwargs)
 
 
-class ExchangeTradingAlgorithm(TradingAlgorithm):
+class ExchangeTradingAlgorithmBase(TradingAlgorithm):
     def __init__(self, *args, **kwargs):
-        self.exchange = kwargs.pop('exchange', None)
-        self.algo_namespace = kwargs.pop('algo_namespace', None)
-        self.live_graph = kwargs.pop('live_graph', None)
+        self.exchanges = kwargs.pop('exchanges', None)
 
-        self._clock = None
-        self.minute_stats = deque(maxlen=60)
+        super(ExchangeTradingAlgorithmBase, self).__init__(*args, **kwargs)
 
-        self.pnl_stats = get_algo_df(self.algo_namespace, 'pnl_stats')
-
-        self.custom_signals_stats = \
-            get_algo_df(self.algo_namespace, 'custom_signals_stats')
-
-        self.exposure_stats = \
-            get_algo_df(self.algo_namespace, 'exposure_stats')
-
-        self.is_running = True
-
-        self.retry_check_open_orders = 5
-        self.retry_synchronize_portfolio = 5
-        self.retry_get_open_orders = 5
-        self.retry_order = 2
-        self.retry_delay = 5
-
-        self.stats_minutes = 5
-
-        super(self.__class__, self).__init__(*args, **kwargs)
-        # self._create_minute_writer()
-
-        signal.signal(signal.SIGINT, self.signal_handler)
-
-        log.info('exchange trading algorithm successfully initialized')
-
-    def _create_minute_writer(self):
-        root = get_exchange_minute_writer_root(self.exchange.name)
-        filename = os.path.join(root, 'metadata.json')
-
-        if os.path.isfile(filename):
-            writer = BcolzMinuteBarWriter.open(
-                root, self.sim_params.end_session)
-        else:
-            writer = BcolzMinuteBarWriter(
-                rootdir=root,
-                calendar=self.trading_calendar,
-                minutes_per_day=1440,
-                start_session=self.sim_params.start_session,
-                end_session=self.sim_params.end_session,
-                write_metadata=True
-            )
-
-        self.exchange.minute_writer = writer
-        self.exchange.minute_reader = BcolzMinuteBarReader(root)
-
-    def signal_handler(self, signal, frame):
-        self.is_running = False
-
-        if self._analyze is None:
-            log.info('Interruption signal detected {}, exiting the '
-                     'algorithm'.format(signal))
-
-        else:
-            log.info('Interruption signal detected {}, calling `analyze()` '
-                     'before exiting the algorithm'.format(signal))
-
-            algo_folder = get_algo_folder(self.algo_namespace)
-            folder = join(algo_folder, 'daily_perf')
-            files = [f for f in listdir(folder) if isfile(join(folder, f))]
-
-            daily_perf_list = []
-            for item in files:
-                filename = join(folder, item)
-                with open(filename, 'rb') as handle:
-                    daily_perf_list.append(pickle.load(handle))
-
-            stats = pd.DataFrame(daily_perf_list)
-
-            self.analyze(stats)
-
-        sys.exit(0)
-
-    @property
-    def clock(self):
-        if self._clock is None:
-            return self._create_clock()
-        else:
-            return self._clock
-
-    def _create_clock(self):
-
-        # The calendar's execution times are the minutes over which we actually
-        # want to run the clock. Typically the execution times simply adhere to
-        # the market open and close times. In the case of the futures calendar,
-        # for example, we only want to simulate over a subset of the full 24
-        # hour calendar, so the execution times dictate a market open time of
-        # 6:31am US/Eastern and a close of 5:00pm US/Eastern.
-
-        # In our case, we are trading around the clock, so the market close
-        # corresponds to the last minute of the day.
-
-        # This method is taken from TradingAlgorithm.
-        # The clock has been replaced to use RealtimeClock
-        # TODO: should we apply a time skew? not sure to understand the utility.
-
-        log.debug('creating clock')
-        if self.live_graph:
-            self._clock = LiveGraphClock(
-                self.sim_params.sessions,
-                time_skew=self.exchange.time_skew,
-                context=self
-            )
-        else:
-            self._clock = SimpleClock(
-                self.sim_params.sessions,
-                time_skew=self.exchange.time_skew
-            )
-
-        return self._clock
-
-    def _create_generator(self, sim_params):
-        if self.perf_tracker is None:
-            self.perf_tracker = get_algo_object(
-                algo_name=self.algo_namespace,
-                key='perf_tracker'
-            )
-
-        # Call the simulation trading algorithm for side-effects:
-        # it creates the perf tracker
-        TradingAlgorithm._create_generator(self, sim_params)
-        self.trading_client = ExchangeAlgorithmExecutor(
-            self,
-            sim_params,
-            self.data_portal,
-            self.clock,
-            self._create_benchmark_source(),
-            self.restrictions,
-            universe_func=self._calculate_universe
-        )
-
-        return self.trading_client.transform()
-
-    def updated_portfolio(self):
+    def round_order(self, amount, asset):
         """
-        We skip the entire performance tracker business and update the
-        portfolio directly.
+        We need fractions with cryptocurrencies
+
+        :param amount:
         :return:
         """
-        return self.exchange.portfolio
+        return round_nearest(amount, asset.min_trade_size)
 
-    def updated_account(self):
-        return self.exchange.account
+    @api_method
+    @preprocess(symbol_str=ensure_upper_case)
+    def symbol(self, symbol_str, exchange_name=None):
+        """Lookup an Equity by its ticker symbol.
 
-    def _synchronize_portfolio(self, attempt_index=0):
-        try:
-            self.exchange.synchronize_portfolio()
+        Parameters
+        ----------
+        symbol_str : str
+            The ticker symbol for the equity to lookup.
+        exchange_name: str
+            The name of the exchange containing the symbol
 
-            # Applying the updated last_sales_price to the positions
-            # in the performance tracker. This seems a bit redundant
-            # but it will make sense when we have multiple exchange portfolios
-            # feeding into the same performance tracker.
-            tracker = self.perf_tracker.todays_performance.position_tracker
-            for asset in self.exchange.portfolio.positions:
-                position = self.exchange.portfolio.positions[asset]
-                tracker.update_position(
-                    asset=asset,
-                    last_sale_date=position.last_sale_date,
-                    last_sale_price=position.last_sale_price
-                )
-        except ExchangeRequestError as e:
-            log.warn(
-                'update portfolio attempt {}: {}'.format(attempt_index, e)
-            )
-            if attempt_index < self.retry_synchronize_portfolio:
-                sleep(self.retry_delay)
-                self._synchronize_portfolio(attempt_index + 1)
-            else:
-                raise ExchangePortfolioDataError(
-                    data_type='update-portfolio',
-                    attempts=attempt_index,
-                    error=e
-                )
+        Returns
+        -------
+        equity : Equity
+            The equity that held the ticker symbol on the current
+            symbol lookup date.
 
-    def _check_open_orders(self, attempt_index=0):
-        try:
-            return self.exchange.check_open_orders()
-        except ExchangeRequestError as e:
-            log.warn(
-                'check open orders attempt {}: {}'.format(attempt_index, e)
-            )
-            if attempt_index < self.retry_check_open_orders:
-                sleep(self.retry_delay)
-                return self._check_open_orders(attempt_index + 1)
-            else:
-                raise ExchangePortfolioDataError(
-                    data_type='order-status',
-                    attempts=attempt_index,
-                    error=e
-                )
+        Raises
+        ------
+        SymbolNotFound
+            Raised when the symbols was not held on the current lookup date.
 
-    def add_pnl_stats(self, period_stats):
-        starting = period_stats['starting_cash']
-        current = period_stats['portfolio_value']
-        appreciation = (current / starting) - 1
-        perc = (appreciation * 100) if current != 0 else 0
+        See Also
+        --------
+        :func:`catalyst.api.set_symbol_lookup_date`
+        """
+        # If the user has not set the symbol lookup date,
+        # use the end_session as the date for sybmol->sid resolution.
 
-        log.debug('adding pnl stats: {:6f}%'.format(perc))
+        _lookup_date = self._symbol_lookup_date \
+            if self._symbol_lookup_date is not None \
+            else self.sim_params.end_session
 
-        df = pd.DataFrame(
-            data=[dict(performance=perc)],
-            index=[period_stats['period_close']]
+        if exchange_name is None:
+            exchange = list(self.exchanges.values())[0]
+        else:
+            exchange = self.exchanges[exchange_name]
+
+        return self.asset_finder.lookup_symbol(
+            symbol=symbol_str,
+            exchange=exchange,
+            as_of_date=_lookup_date
         )
-        self.pnl_stats = pd.concat([self.pnl_stats, df])
-
-        save_algo_df(self.algo_namespace, 'pnl_stats', self.pnl_stats)
-
-    def add_custom_signals_stats(self, period_stats):
-        log.debug('adding custom signals stats: {}'.format(self.recorded_vars))
-        df = pd.DataFrame(
-            data=[self.recorded_vars],
-            index=[period_stats['period_close']],
-        )
-        self.custom_signals_stats = pd.concat([self.custom_signals_stats, df])
-
-        save_algo_df(self.algo_namespace, 'custom_signals_stats',
-                     self.custom_signals_stats)
-
-    def add_exposure_stats(self, period_stats):
-        data = dict(
-            long_exposure=period_stats['long_exposure'],
-            base_currency=period_stats['ending_cash']
-        )
-        log.debug('adding exposure stats: {}'.format(data))
-
-        df = pd.DataFrame(
-            data=[data],
-            index=[period_stats['period_close']],
-        )
-        self.exposure_stats = pd.concat([self.exposure_stats, df])
-
-        save_algo_df(self.algo_namespace, 'exposure_stats',
-                     self.exposure_stats)
 
     def prepare_period_stats(self, start_dt, end_dt):
         """
         Creates a dictionary representing the state of the tracker.
 
+        Parameters
+        ----------
+        start_dt: datetime
+        end_dt: datetime
 
+        Notes
+        -----
         I rewrote this in an attempt to better control the stats.
         I don't want things to happen magically through complex logic
         pertaining to backtesting.
@@ -364,7 +196,366 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
 
         return stats
 
+
+class ExchangeTradingAlgorithmBacktest(ExchangeTradingAlgorithmBase):
+    def __init__(self, *args, **kwargs):
+        super(ExchangeTradingAlgorithmBacktest, self).__init__(*args, **kwargs)
+
+        self.blotter = ExchangeBlotter(
+            data_frequency=self.data_frequency,
+            # Default to NeverCancel in catalyst
+            cancel_policy=self.cancel_policy,
+        )
+        log.info('initialized trading algorithm in backtest mode')
+
+    def _calculate_order(self, asset, amount,
+                         limit_price=None, stop_price=None, style=None):
+        # Raises a ZiplineError if invalid parameters are detected.
+        self.validate_order_params(asset,
+                                   amount,
+                                   limit_price,
+                                   stop_price,
+                                   style)
+
+        # Convert deprecated limit_price and stop_price parameters to use
+        # ExecutionStyle objects.
+        style = self.__convert_order_params_for_blotter(limit_price,
+                                                        stop_price,
+                                                        style)
+        return amount, style
+
+    @staticmethod
+    def __convert_order_params_for_blotter(limit_price, stop_price, style):
+        """
+        Helper method for converting deprecated limit_price and stop_price
+        arguments into ExecutionStyle instances.
+
+        This function assumes that either style == None or (limit_price,
+        stop_price) == (None, None).
+        """
+        if style:
+            assert (limit_price, stop_price) == (None, None)
+            return style
+        if limit_price and stop_price:
+            return ExchangeStopLimitOrder(limit_price, stop_price)
+        if limit_price:
+            return ExchangeLimitOrder(limit_price)
+        if stop_price:
+            return ExchangeStopOrder(stop_price)
+        else:
+            return MarketOrder()
+
+
+class ExchangeTradingAlgorithmLive(ExchangeTradingAlgorithmBase):
+    def __init__(self, *args, **kwargs):
+        self.algo_namespace = kwargs.pop('algo_namespace', None)
+        self.live_graph = kwargs.pop('live_graph', None)
+
+        self._clock = None
+        self.minute_stats = deque(maxlen=60)
+
+        self.pnl_stats = get_algo_df(self.algo_namespace, 'pnl_stats')
+
+        self.custom_signals_stats = \
+            get_algo_df(self.algo_namespace, 'custom_signals_stats')
+
+        self.exposure_stats = \
+            get_algo_df(self.algo_namespace, 'exposure_stats')
+
+        self.is_running = True
+
+        self.retry_check_open_orders = 5
+        self.retry_synchronize_portfolio = 5
+        self.retry_get_open_orders = 5
+        self.retry_order = 2
+        self.retry_delay = 5
+
+        self.stats_minutes = 5
+
+        super(ExchangeTradingAlgorithmLive, self).__init__(*args, **kwargs)
+        # TODO: fix precision before re-enabling
+        # self._create_minute_writer()
+
+        signal.signal(signal.SIGINT, self.signal_handler)
+
+        log.info('initialized trading algorithm in live mode')
+
+    def _create_minute_writer(self):
+        root = get_exchange_minute_writer_root(self.exchange.name)
+        filename = os.path.join(root, 'metadata.json')
+
+        if os.path.isfile(filename):
+            writer = BcolzMinuteBarWriter.open(
+                root, self.sim_params.end_session)
+        else:
+            # TODO: need to be able to write more precise numbers
+            writer = BcolzMinuteBarWriter(
+                rootdir=root,
+                calendar=self.trading_calendar,
+                minutes_per_day=1440,
+                start_session=self.sim_params.start_session,
+                end_session=self.sim_params.end_session,
+                write_metadata=True
+            )
+
+        self.exchange.minute_writer = writer
+        self.exchange.minute_reader = BcolzMinuteBarReader(root)
+
+    def signal_handler(self, signal, frame):
+        """
+        Handles the keyboard interruption signal.
+
+        Parameters
+        ----------
+        signal
+        frame
+
+        Returns
+        -------
+
+        """
+        self.is_running = False
+
+        if self._analyze is None:
+            log.info('Interruption signal detected {}, exiting the '
+                     'algorithm'.format(signal))
+
+        else:
+            log.info('Interruption signal detected {}, calling `analyze()` '
+                     'before exiting the algorithm'.format(signal))
+
+            algo_folder = get_algo_folder(self.algo_namespace)
+            folder = join(algo_folder, 'daily_perf')
+            files = [f for f in listdir(folder) if isfile(join(folder, f))]
+
+            daily_perf_list = []
+            for item in files:
+                filename = join(folder, item)
+                with open(filename, 'rb') as handle:
+                    daily_perf_list.append(pickle.load(handle))
+
+            stats = pd.DataFrame(daily_perf_list)
+
+            self.analyze(stats)
+
+        sys.exit(0)
+
+    @property
+    def clock(self):
+        if self._clock is None:
+            return self._create_clock()
+        else:
+            return self._clock
+
+    def _create_clock(self):
+
+        # The calendar's execution times are the minutes over which we actually
+        # want to run the clock. Typically the execution times simply adhere to
+        # the market open and close times. In the case of the futures calendar,
+        # for example, we only want to simulate over a subset of the full 24
+        # hour calendar, so the execution times dictate a market open time of
+        # 6:31am US/Eastern and a close of 5:00pm US/Eastern.
+
+        # In our case, we are trading around the clock, so the market close
+        # corresponds to the last minute of the day.
+
+        # This method is taken from TradingAlgorithm.
+        # The clock has been replaced to use RealtimeClock
+        # TODO: should we apply a time skew? not sure to understand the utility.
+
+        log.debug('creating clock')
+        if self.live_graph:
+            self._clock = LiveGraphClock(
+                self.sim_params.sessions,
+                context=self
+            )
+        else:
+            self._clock = SimpleClock(
+                self.sim_params.sessions,
+            )
+
+        return self._clock
+
+    def _create_generator(self, sim_params):
+        if self.perf_tracker is None:
+            self.perf_tracker = get_algo_object(
+                algo_name=self.algo_namespace,
+                key='perf_tracker'
+            )
+
+        # Call the simulation trading algorithm for side-effects:
+        # it creates the perf tracker
+        TradingAlgorithm._create_generator(self, sim_params)
+        self.trading_client = ExchangeAlgorithmExecutor(
+            self,
+            sim_params,
+            self.data_portal,
+            self.clock,
+            self._create_benchmark_source(),
+            self.restrictions,
+            universe_func=self._calculate_universe
+        )
+
+        return self.trading_client.transform()
+
+    def updated_portfolio(self):
+        """
+        We skip the entire performance tracker business and update the
+        portfolio directly.
+
+        Returns
+        -------
+        ExchangePortfolio
+
+        """
+        # TODO: build cumulative portfolio
+        return self.perf_tracker.get_portfolio(False)
+
+    def updated_account(self):
+        return self.perf_tracker.get_account(False)
+
+    def _synchronize_portfolio(self, attempt_index=0):
+        try:
+            for exchange_name in self.exchanges:
+                exchange = self.exchanges[exchange_name]
+
+                exchange.synchronize_portfolio()
+
+                # Applying the updated last_sales_price to the positions
+                # in the performance tracker. This seems a bit redundant
+                # but it will make sense when we have multiple exchange portfolios
+                # feeding into the same performance tracker.
+                tracker = self.perf_tracker.todays_performance.position_tracker
+                for asset in exchange.portfolio.positions:
+                    position = exchange.portfolio.positions[asset]
+                    tracker.update_position(
+                        asset=asset,
+                        last_sale_date=position.last_sale_date,
+                        last_sale_price=position.last_sale_price
+                    )
+        except ExchangeRequestError as e:
+            log.warn(
+                'update portfolio attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_synchronize_portfolio:
+                sleep(self.retry_delay)
+                self._synchronize_portfolio(attempt_index + 1)
+            else:
+                raise ExchangePortfolioDataError(
+                    data_type='update-portfolio',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def _check_open_orders(self, attempt_index=0):
+        try:
+            orders = list()
+            for exchange_name in self.exchanges:
+                exchange = self.exchanges[exchange_name]
+                exchange_orders = exchange.check_open_orders()
+
+                orders += exchange_orders
+
+            return orders
+        except ExchangeRequestError as e:
+            log.warn(
+                'check open orders attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_check_open_orders:
+                sleep(self.retry_delay)
+                return self._check_open_orders(attempt_index + 1)
+            else:
+                raise ExchangePortfolioDataError(
+                    data_type='order-status',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def add_pnl_stats(self, period_stats):
+        """
+        Save p&l stats.
+
+        Parameters
+        ----------
+        period_stats
+
+        Returns
+        -------
+
+        """
+        starting = period_stats['starting_cash']
+        current = period_stats['portfolio_value']
+        appreciation = (current / starting) - 1
+        perc = (appreciation * 100) if current != 0 else 0
+
+        log.debug('adding pnl stats: {:6f}%'.format(perc))
+
+        df = pd.DataFrame(
+            data=[dict(performance=perc)],
+            index=[period_stats['period_close']]
+        )
+        self.pnl_stats = pd.concat([self.pnl_stats, df])
+
+        save_algo_df(self.algo_namespace, 'pnl_stats', self.pnl_stats)
+
+    def add_custom_signals_stats(self, period_stats):
+        """
+        Save custom signals stats.
+
+        Parameters
+        ----------
+        period_stats
+
+        Returns
+        -------
+
+        """
+        log.debug('adding custom signals stats: {}'.format(self.recorded_vars))
+        df = pd.DataFrame(
+            data=[self.recorded_vars],
+            index=[period_stats['period_close']],
+        )
+        self.custom_signals_stats = pd.concat([self.custom_signals_stats, df])
+
+        save_algo_df(self.algo_namespace, 'custom_signals_stats',
+                     self.custom_signals_stats)
+
+    def add_exposure_stats(self, period_stats):
+        """
+        Save exposure stats.
+
+        Parameters
+        ----------
+        period_stats
+
+        Returns
+        -------
+
+        """
+        data = dict(
+            long_exposure=period_stats['long_exposure'],
+            base_currency=period_stats['ending_cash']
+        )
+        log.debug('adding exposure stats: {}'.format(data))
+
+        df = pd.DataFrame(
+            data=[data],
+            index=[period_stats['period_close']],
+        )
+        self.exposure_stats = pd.concat([self.exposure_stats, df])
+
+        save_algo_df(self.algo_namespace, 'exposure_stats',
+                     self.exposure_stats)
+
     def handle_data(self, data):
+        """
+        Wrapper around the handle_data method of each algo.
+
+        Parameters
+        ----------
+        data
+
+        """
         if not self.is_running:
             return
 
@@ -394,14 +585,23 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
             self.minute_stats.append(minute_stats)
 
             self.add_pnl_stats(minute_stats)
-            self.add_custom_signals_stats(minute_stats)
+            if self.recorded_vars:
+                self.add_custom_signals_stats(minute_stats)
+                recorded_cols = list(self.recorded_vars.keys())
+            else:
+                recorded_cols = None
+
             self.add_exposure_stats(minute_stats)
 
             print_df = pd.DataFrame(list(self.minute_stats))
-            log.debug(
+            log.info(
                 'statistics for the last {stats_minutes} minutes:\n{stats}'.format(
                     stats_minutes=self.stats_minutes,
-                    stats=get_pretty_stats(print_df, self.stats_minutes)
+                    stats=get_pretty_stats(
+                        stats_df=print_df,
+                        recorded_cols=recorded_cols,
+                        num_rows=self.stats_minutes
+                    )
                 ))
 
             today = pd.to_datetime('today', utc=True)
@@ -419,6 +619,7 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
         except Exception as e:
             log.warn('unable to calculate performance: {}'.format(e))
 
+        # TODO: pickle does not seem to work in python 3
         try:
             save_algo_object(
                 algo_name=self.algo_namespace,
@@ -429,11 +630,13 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
             log.warn('unable to save minute perfs to disk: {}'.format(e))
 
         try:
-            save_algo_object(
-                algo_name=self.algo_namespace,
-                key='portfolio_{}'.format(self.exchange.name),
-                obj=self.exchange.portfolio
-            )
+            for exchange_name in self.exchanges:
+                exchange = self.exchanges[exchange_name]
+                save_algo_object(
+                    algo_name=self.algo_namespace,
+                    key='portfolio_{}'.format(exchange_name),
+                    obj=exchange.portfolio
+                )
         except Exception as e:
             log.warn('unable to save portfolio to disk: {}'.format(e))
 
@@ -445,9 +648,10 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
                style=None,
                attempt_index=0):
         try:
-            return self.exchange.order(asset, amount, limit_price,
-                                       stop_price,
-                                       style)
+            exchange = self.exchanges[asset.exchange]
+            return exchange.order(asset, amount, limit_price,
+                                  stop_price,
+                                  style)
         except ExchangeRequestError as e:
             log.warn(
                 'order attempt {}: {}'.format(attempt_index, e)
@@ -466,41 +670,71 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
 
     @api_method
     @disallowed_in_before_trading_start(OrderInBeforeTradingStart())
+    @expect_types(asset=TradingPair)
     def order(self,
               asset,
               amount,
               limit_price=None,
               stop_price=None,
               style=None):
+        """
+        We use the exchange specific portfolio to place orders.
+        The cumulative portfolio does not contain open orders but exchange
+        portfolios do.
+
+        Parameters
+        ----------
+        asset: TradingPair
+        amount: float
+        limit_price: float
+        stop_price: float
+        style: Style
+        order: Order
+            The catalyst order object or None
+        """
         amount, style = self._calculate_order(asset, amount,
                                               limit_price, stop_price,
                                               style)
 
         order_id = self._order(asset, amount, limit_price, stop_price, style)
 
+        exchange = self.exchanges[asset.exchange]
+        exchange_portfolio = exchange.portfolio
         if order_id is not None:
-            order = self.portfolio.open_orders[order_id]
-            self.perf_tracker.process_order(order)
-            return order
+
+            if order_id in exchange_portfolio.open_orders:
+                order = exchange_portfolio.open_orders[order_id]
+                self.perf_tracker.process_order(order)
+                return order
+
+            else:
+                raise OrphanOrderError(
+                    order_id=order_id,
+                    exchange=exchange.name
+                )
         else:
+            log.warn('unable to order {} {} on exchange {}'.format(
+                amount, asset.symbol, asset.exchange))
             return None
 
-    def round_order(self, amount):
-        """
-        We need fractions with cryptocurrencies
-
-        :param amount:
-        :return:
-        """
-        return amount
-
     @api_method
     def batch_market_order(self, share_counts):
         raise NotImplementedError()
 
     def _get_open_orders(self, asset=None, attempt_index=0):
         try:
-            return self.exchange.get_open_orders(asset)
+            if asset:
+                exchange = self.exchanges[asset.exchange]
+                return exchange.get_open_orders(asset)
+
+            else:
+                open_orders = []
+                for exchange_name in self.exchanges:
+                    exchange = self.exchanges[exchange_name]
+                    exchange_orders = exchange.get_open_orders()
+                    open_orders.append(exchange_orders)
+
+                return open_orders
         except ExchangeRequestError as e:
             log.warn(
                 'open orders attempt {}: {}'.format(attempt_index, e)
@@ -519,15 +753,57 @@ class ExchangeTradingAlgorithm(TradingAlgorithm):
                         'get_open_orders. Use `asset` instead.')
     @api_method
     def get_open_orders(self, asset=None):
+        """Retrieve all of the current open orders.
+
+        Parameters
+        ----------
+        asset : Asset
+            If passed and not None, return only the open orders for the given
+            asset instead of all open orders.
+
+        Returns
+        -------
+        open_orders : dict[list[Order]] or list[Order]
+            If no asset is passed this will return a dict mapping Assets
+            to a list containing all the open orders for the asset.
+            If an asset is passed then this will return a list of the open
+            orders for this asset.
+        """
         return self._get_open_orders(asset)
 
     @api_method
-    def get_order(self, order_id):
-        return self.exchange.get_order(order_id)
+    def get_order(self, order_id, exchange_name):
+        """Lookup an order based on the order id returned from one of the
+        order functions.
+
+        Parameters
+        ----------
+        order_id : str
+            The unique identifier for the order.
+
+        Returns
+        -------
+        order : Order
+            The order object.
+        execution_price: float
+            The execution price per share of the order
+        """
+        exchange = self.exchanges[exchange_name]
+        return exchange.get_order(order_id)
 
     @api_method
-    def cancel_order(self, order_param):
+    def cancel_order(self, order_param, exchange_name):
+        """Cancel an open order.
+
+        Parameters
+        ----------
+        order_param : str or Order
+            The order_id or order object to cancel.
+        """
+        exchange = self.exchanges[exchange_name]
+
         order_id = order_param
         if isinstance(order_param, zp.Order):
             order_id = order_param.id
-        self.exchange.cancel_order(order_id)
+
+        exchange.cancel_order(order_id)

catalyst/exchange/exchange_bcolz.py

@@ -0,0 +1,98 @@
+import numpy as np
+
+from catalyst import get_calendar
+from catalyst.data.minute_bars import BcolzMinuteBarReader, \
+    BcolzMinuteBarWriter
+
+
+class BcolzExchangeBarWriter(BcolzMinuteBarWriter):
+    def __init__(self, *args, **kwargs):
+        self._data_frequency = kwargs.pop('data_frequency', None)
+        kwargs.pop('minutes_per_day', None)
+        kwargs.pop('calendar', None)
+
+        end_session = kwargs.pop('end_session', None)
+        if end_session is not None:
+            end_session = end_session.floor('1d')
+
+        minutes_per_day = 1440 if self._data_frequency == 'minute' else 1
+        default_ohlc_ratio = kwargs.pop('default_ohlc_ratio', 100000000)
+        calendar = get_calendar('OPEN')
+
+        super(BcolzExchangeBarWriter, self) \
+            .__init__(*args, **dict(kwargs,
+                                    minutes_per_day=minutes_per_day,
+                                    default_ohlc_ratio=default_ohlc_ratio,
+                                    calendar=calendar,
+                                    end_session=end_session
+                                    ))
+
+
+class BcolzExchangeBarReader(BcolzMinuteBarReader):
+    def __init__(self, *args, **kwargs):
+        self._data_frequency = kwargs.pop('data_frequency', None)
+
+        super(BcolzExchangeBarReader, self).__init__(*args, **kwargs)
+
+    @property
+    def data_frequency(self):
+        return self._data_frequency
+
+    def load_raw_arrays(self, fields, start_dt, end_dt, sids):
+        """
+        Parameters
+        ----------
+        fields : list of str
+           'open', 'high', 'low', 'close', or 'volume'
+        start_dt: Timestamp
+           Beginning of the window range.
+        end_dt: Timestamp
+           End of the window range.
+        sids : list of int
+           The asset identifiers in the window.
+
+        Returns
+        -------
+        list of np.ndarray
+            A list with an entry per field of ndarrays with shape
+            (minutes in range, sids) with a dtype of float64, containing the
+            values for the respective field over start and end dt range.
+        """
+        start_idx = self._find_position_of_minute(start_dt)
+        end_idx = self._find_position_of_minute(end_dt)
+
+        periods = self.calendar.minutes_in_range(start_dt, end_dt) \
+            if self.data_frequency == 'minute' \
+            else self.calendar.sessions_in_range(start_dt, end_dt)
+
+        num_days = len(periods)
+        shape = num_days, len(sids)
+
+        all_fields = fields[:]
+        if len(all_fields) == 1 and all_fields[0] == 'volume':
+            all_fields.insert(0, 'close')
+
+        mask = None
+        data = []
+        for field in all_fields:
+            if field != 'volume':
+                out = np.full(shape, np.nan)
+            else:
+                out = np.zeros(shape, dtype=np.float64)
+
+            for i, sid in enumerate(sids):
+                carray = self._open_minute_file(field, sid)
+                a = carray[start_idx:end_idx + 1]
+
+                if mask is None:
+                    mask = a != 0
+
+                inverse_ratio = self._ohlc_ratio_inverse_for_sid(sid)
+                out[:len(mask), i][mask] = (
+                    a[mask] * inverse_ratio
+                )
+
+            if field in fields:
+                data.append(out)
+
+        return data

catalyst/exchange/exchange_blotter.py

@@ -0,0 +1,134 @@
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+
+from catalyst.constants import LOG_LEVEL
+from catalyst.finance.blotter import Blotter
+from catalyst.finance.commission import CommissionModel
+from catalyst.finance.slippage import SlippageModel
+from catalyst.finance.transaction import create_transaction
+
+log = Logger('exchange_blotter', level=LOG_LEVEL)
+
+# It seems like we need to accept greater slippage risk in cryptos
+# Orders won't often close at Equity levels.
+# TODO: should work with set_commission and set_slippage
+DEFAULT_SLIPPAGE_SPREAD = 0.0001
+DEFAULT_MAKER_FEE = 0.0015
+DEFAULT_TAKER_FEE = 0.0025
+
+
+class TradingPairFeeSchedule(CommissionModel):
+    """
+    Calculates a commission for a transaction based on a per percentage fee.
+
+    Parameters
+    ----------
+    fee : float, optional
+        The percentage fee.
+    """
+
+    def __init__(self,
+                 maker_fee=DEFAULT_MAKER_FEE,
+                 taker_fee=DEFAULT_TAKER_FEE):
+        self.maker_fee = maker_fee
+        self.taker_fee = taker_fee
+
+    def __repr__(self):
+        return (
+            '{class_name}(maker_fee={maker_fee}, '
+            'taker_fee={taker_fee})'.format(
+                class_name=self.__class__.__name__,
+                maker_fee=self.maker_fee,
+                taker_fee=self.taker_fee,
+            )
+        )
+
+    def calculate(self, order, transaction):
+        """
+        Calculate the final fee based on the order parameters.
+
+        :param order:
+        :param transaction:
+
+        :return float:
+            The total commission.
+        """
+        cost = abs(transaction.amount) * transaction.price
+
+        # Assuming just the taker fee for now
+        fee = cost * self.taker_fee
+        return fee
+
+
+class TradingPairFixedSlippage(SlippageModel):
+    """
+    Model slippage as a fixed spread.
+
+    Parameters
+    ----------
+    spread : float, optional
+        spread / 2 will be added to buys and subtracted from sells.
+    """
+
+    def __init__(self, spread=DEFAULT_SLIPPAGE_SPREAD):
+        super(TradingPairFixedSlippage, self).__init__()
+        self.spread = spread
+
+    def __repr__(self):
+        return '{class_name}(spread={spread})'.format(
+            class_name=self.__class__.__name__, spread=self.spread,
+        )
+
+    def simulate(self, data, asset, orders_for_asset):
+        self._volume_for_bar = 0
+
+        price = data.current(asset, 'close')
+
+        dt = data.current_dt
+        for order in orders_for_asset:
+            if order.open_amount == 0:
+                continue
+
+            order.check_triggers(price, dt)
+            if not order.triggered:
+                log.debug('order has not reached the trigger at current '
+                          'price {}'.format(price))
+                continue
+
+            execution_price, execution_volume = self.process_order(data, order)
+
+            transaction = create_transaction(
+                order, dt, execution_price, execution_volume
+            )
+
+            self._volume_for_bar += abs(transaction.amount)
+            yield order, transaction
+
+    def process_order(self, data, order):
+        price = data.current(order.asset, 'close')
+
+        if order.amount > 0:
+            # Buy order
+            adj_price = price * (1 + self.spread)
+        else:
+            # Sell order
+            adj_price = price * (1 - self.spread)
+
+        log.debug('added slippage to price: {} => {}'.format(price, adj_price))
+
+        return adj_price, order.amount
+
+
+class ExchangeBlotter(Blotter):
+    def __init__(self, *args, **kwargs):
+        super(ExchangeBlotter, self).__init__(*args, **kwargs)
+
+        # Using the equity models for now
+        # We may be able to define more sophisticated models based on the fee
+        # structure of each exchange.
+        self.slippage_models = {
+            TradingPair: TradingPairFixedSlippage()
+        }
+        self.commission_models = {
+            TradingPair: TradingPairFeeSchedule()
+        }

catalyst/exchange/exchange_bundle.py

@@ -0,0 +1,860 @@
+import os
+import shutil
+from itertools import chain
+
+import pandas as pd
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+from pandas.tslib import Timestamp
+from pytz import UTC
+from six import itervalues
+
+from catalyst import get_calendar
+from catalyst.constants import LOG_LEVEL
+from catalyst.data.minute_bars import BcolzMinuteOverlappingData, \
+    BcolzMinuteBarMetadata
+from catalyst.exchange.bundle_utils import range_in_bundle, \
+    get_bcolz_chunk, get_delta, get_month_start_end, \
+    get_year_start_end, get_df_from_arrays, get_start_dt, get_period_label
+from catalyst.exchange.exchange_bcolz import BcolzExchangeBarReader, \
+    BcolzExchangeBarWriter
+from catalyst.exchange.exchange_errors import EmptyValuesInBundleError, \
+    TempBundleNotFoundError, \
+    NoDataAvailableOnExchange, \
+    PricingDataNotLoadedError
+from catalyst.exchange.exchange_utils import get_exchange_folder
+from catalyst.utils.cli import maybe_show_progress
+from catalyst.utils.paths import ensure_directory
+import os
+import shutil
+from itertools import chain
+
+import pandas as pd
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+from pandas.tslib import Timestamp
+from pytz import UTC
+from six import itervalues
+
+from catalyst import get_calendar
+from catalyst.constants import LOG_LEVEL
+from catalyst.data.minute_bars import BcolzMinuteOverlappingData, \
+    BcolzMinuteBarMetadata
+from catalyst.exchange.bundle_utils import range_in_bundle, \
+    get_bcolz_chunk, get_delta, get_month_start_end, \
+    get_year_start_end, get_df_from_arrays, get_start_dt, get_period_label
+from catalyst.exchange.exchange_bcolz import BcolzExchangeBarReader, \
+    BcolzExchangeBarWriter
+from catalyst.exchange.exchange_errors import EmptyValuesInBundleError, \
+    TempBundleNotFoundError, \
+    NoDataAvailableOnExchange, \
+    PricingDataNotLoadedError
+from catalyst.exchange.exchange_utils import get_exchange_folder
+from catalyst.utils.cli import maybe_show_progress
+from catalyst.utils.paths import ensure_directory
+
+log = Logger('exchange_bundle', level=LOG_LEVEL)
+
+BUNDLE_NAME_TEMPLATE = os.path.join('{root}', '{frequency}_bundle')
+
+
+def _cachpath(symbol, type_):
+    return '-'.join([symbol, type_])
+
+
+class ExchangeBundle:
+    def __init__(self, exchange):
+        self.exchange = exchange
+        self.minutes_per_day = 1440
+        self.default_ohlc_ratio = 1000000
+        self._writers = dict()
+        self._readers = dict()
+        self.calendar = get_calendar('OPEN')
+
+    def get_assets(self, include_symbols, exclude_symbols):
+        # TODO: filter exclude symbols assets
+        if include_symbols is not None:
+            include_symbols_list = include_symbols.split(',')
+
+            return self.exchange.get_assets(include_symbols_list)
+
+        else:
+            return self.exchange.get_assets()
+
+    def get_reader(self, data_frequency, path=None):
+        """
+        Get a data writer object, either a new object or from cache
+
+        Returns
+        -------
+        BcolzMinuteBarReader | BcolzDailyBarReader
+
+        """
+        if path is None:
+            root = get_exchange_folder(self.exchange.name)
+            path = BUNDLE_NAME_TEMPLATE.format(
+                root=root,
+                frequency=data_frequency
+            )
+
+        if path in self._readers and self._readers[path] is not None:
+            return self._readers[path]
+
+        try:
+            self._readers[path] = BcolzExchangeBarReader(
+                rootdir=path,
+                data_frequency=data_frequency
+            )
+        except IOError:
+            self._readers[path] = None
+
+        return self._readers[path]
+
+    def update_metadata(self, writer, start_dt, end_dt):
+        pass
+
+    def get_writer(self, start_dt, end_dt, data_frequency):
+        """
+        Get a data writer object, either a new object or from cache
+
+        Returns
+        -------
+        BcolzMinuteBarWriter | BcolzDailyBarWriter
+
+        """
+        root = get_exchange_folder(self.exchange.name)
+        path = BUNDLE_NAME_TEMPLATE.format(
+            root=root,
+            frequency=data_frequency
+        )
+
+        if path in self._writers:
+            return self._writers[path]
+
+        ensure_directory(path)
+
+        if len(os.listdir(path)) > 0:
+
+            metadata = BcolzMinuteBarMetadata.read(path)
+
+            write_metadata = False
+            if start_dt < metadata.start_session:
+                write_metadata = True
+                start_session = start_dt
+            else:
+                start_session = metadata.start_session
+
+            if end_dt > metadata.end_session:
+                write_metadata = True
+
+                end_session = end_dt
+            else:
+                end_session = metadata.end_session
+
+            self._writers[path] = \
+                BcolzExchangeBarWriter(
+                    rootdir=path,
+                    start_session=start_session,
+                    end_session=end_session,
+                    write_metadata=write_metadata,
+                    data_frequency=data_frequency
+                )
+        else:
+            self._writers[path] = BcolzExchangeBarWriter(
+                rootdir=path,
+                start_session=start_dt,
+                end_session=end_dt,
+                write_metadata=True,
+                data_frequency=data_frequency
+            )
+
+        return self._writers[path]
+
+    def filter_existing_assets(self, assets, start_dt, end_dt, data_frequency):
+        """
+        For each asset, get the close on the start and end dates of the chunk.
+            If the data exists, the chunk ingestion is complete.
+            If any data is missing we ingest the data.
+
+        Parameters
+        ----------
+        assets: list[TradingPair]
+            The assets is scope.
+        start_dt: datetime
+            The chunk start date.
+        end_dt: datetime
+            The chunk end date.
+        data_frequency: str
+
+        Returns
+        -------
+        list[TradingPair]
+            The assets missing from the bundle
+        """
+        reader = self.get_reader(data_frequency)
+        missing_assets = []
+        for asset in assets:
+            has_data = range_in_bundle(asset, start_dt, end_dt, reader)
+
+            if not has_data:
+                missing_assets.append(asset)
+
+        return missing_assets
+
+    def _write(self, data, writer, data_frequency):
+        try:
+            writer.write(
+                data=data,
+                show_progress=False,
+                invalid_data_behavior='raise'
+            )
+        except BcolzMinuteOverlappingData as e:
+            log.debug('chunk already exists: {}'.format(e))
+        except Exception as e:
+            log.warn('error when writing data: {}, trying again'.format(e))
+
+            # This is workaround, there is an issue with empty
+            # session_label when using a newly created writer
+            del self._writers[writer._rootdir]
+
+            writer = self.get_writer(writer._start_session,
+                                     writer._end_session, data_frequency)
+            writer.write(
+                data=data,
+                show_progress=False,
+                invalid_data_behavior='raise'
+            )
+
+    def get_calendar_periods_range(self, start_dt, end_dt, data_frequency):
+        """
+        Get a list of dates for the specified range.
+
+        Parameters
+        ----------
+        start_dt: datetime
+        end_dt: datetime
+        data_frequency: str
+
+        Returns
+        -------
+        list[datetime]
+
+        """
+        return self.calendar.minutes_in_range(start_dt, end_dt) \
+            if data_frequency == 'minute' \
+            else self.calendar.sessions_in_range(start_dt, end_dt)
+
+    def ingest_df(self, ohlcv_df, data_frequency, asset, writer,
+                  empty_rows_behavior='strip'):
+        """
+        Ingest a DataFrame of OHLCV data for a given market.
+
+        Parameters
+        ----------
+        ohlcv_df: DataFrame
+        data_frequency: str
+        asset: TradingPair
+        writer:
+        empty_rows_behavior: str
+
+        """
+        if empty_rows_behavior is not 'ignore':
+            nan_rows = ohlcv_df[ohlcv_df.isnull().T.any().T].index
+
+            if len(nan_rows) > 0:
+                dates = []
+                previous_date = None
+                for row_date in nan_rows.values:
+                    row_date = pd.to_datetime(row_date)
+
+                    if previous_date is None:
+                        dates.append(row_date)
+
+                    else:
+                        seq_date = previous_date + get_delta(1, data_frequency)
+
+                        if row_date > seq_date:
+                            dates.append(previous_date)
+                            dates.append(row_date)
+
+                    previous_date = row_date
+
+                dates.append(pd.to_datetime(nan_rows.values[-1]))
+
+                name = '{} from {} to {}'.format(
+                    asset.symbol, ohlcv_df.index[0], ohlcv_df.index[-1]
+                )
+                if empty_rows_behavior == 'warn':
+                    log.warn(
+                        '\n{name} with end minute {end_minute} has empty rows '
+                        'in ranges: {dates}'.format(
+                            name=name,
+                            end_minute=asset.end_minute,
+                            dates=dates
+                        )
+                    )
+
+                elif empty_rows_behavior == 'raise':
+                    raise EmptyValuesInBundleError(
+                        name=name,
+                        end_minute=asset.end_minute,
+                        dates=dates
+                    )
+                else:
+                    ohlcv_df.dropna(inplace=True)
+
+        data = []
+        if not ohlcv_df.empty:
+            ohlcv_df.sort_index(inplace=True)
+            data.append((asset.sid, ohlcv_df))
+
+        self._write(data, writer, data_frequency)
+
+    def ingest_ctable(self, asset, data_frequency, period,
+                      writer, empty_rows_behavior='strip', cleanup=False):
+        """
+        Merge a ctable bundle chunk into the main bundle for the exchange.
+
+        Parameters
+        ----------
+        asset: TradingPair
+        data_frequency: str
+        period: str
+        writer:
+        empty_rows_behavior: str
+            Ensure that the bundle does not have any missing data.
+
+        cleanup: bool
+            Remove the temp bundle directory after ingestion.
+
+        :return:
+        """
+        # Download and extract the bundle
+        path = get_bcolz_chunk(
+            exchange_name=self.exchange.name,
+            symbol=asset.symbol,
+            data_frequency=data_frequency,
+            period=period
+        )
+
+        reader = self.get_reader(data_frequency, path=path)
+        if reader is None:
+            try:
+                log.warn('the reader is unable to use bundle: {}, '
+                         'deleting it.'.format(path))
+                shutil.rmtree(path)
+
+            except Exception as e:
+                log.warn('unable to remove temp bundle: {}'.format(e))
+
+            raise TempBundleNotFoundError(path=path)
+
+        start_dt = reader.first_trading_day
+        end_dt = reader.last_available_dt
+
+        if data_frequency == 'daily':
+            end_dt = end_dt - pd.Timedelta(hours=23, minutes=59)
+
+        arrays = None
+        try:
+            arrays = reader.load_raw_arrays(
+                sids=[asset.sid],
+                fields=['open', 'high', 'low', 'close', 'volume'],
+                start_dt=start_dt,
+                end_dt=end_dt
+            )
+        except Exception as e:
+            log.warn('skipping ctable for {} from {} to {}: {}'.format(
+                asset.symbol, start_dt, end_dt, e
+            ))
+
+        if not arrays:
+            return reader._rootdir
+
+        periods = self.get_calendar_periods_range(
+            start_dt, end_dt, data_frequency
+        )
+        df = get_df_from_arrays(arrays, periods)
+        self.ingest_df(
+            ohlcv_df=df,
+            data_frequency=data_frequency,
+            asset=asset,
+            writer=writer,
+            empty_rows_behavior=empty_rows_behavior
+        )
+
+        if cleanup:
+            log.debug(
+                'removing bundle folder following ingestion: {}'.format(
+                    reader._rootdir)
+            )
+            shutil.rmtree(reader._rootdir)
+
+        return reader._rootdir
+
+    def get_adj_dates(self, start, end, assets, data_frequency):
+        """
+        Contains a date range to the trading availability of the specified
+        markets.
+
+        Parameters
+        ----------
+        start: datetime
+        end: datetime
+        assets: list[TradingPair]
+        data_frequency: str
+
+        Returns
+        -------
+        datetime, datetime
+        """
+        earliest_trade = None
+        last_entry = None
+        for asset in assets:
+            if earliest_trade is None or earliest_trade > asset.start_date:
+                if asset.start_date >= self.calendar.first_session:
+                    earliest_trade = asset.start_date
+
+                else:
+                    earliest_trade = self.calendar.first_session
+
+            end_asset = asset.end_minute if data_frequency == 'minute' else \
+                asset.end_daily
+            if end_asset is not None:
+                if last_entry is None or end_asset > last_entry:
+                    last_entry = end_asset
+
+            else:
+                end = None
+                last_entry = None
+
+        if start is None or \
+                (earliest_trade is not None and earliest_trade > start):
+            start = earliest_trade
+
+        if end is None or (last_entry is not None and end > last_entry):
+            end = last_entry
+
+        if end is None or start is None or start > end:
+            raise NoDataAvailableOnExchange(
+                exchange=[asset.exchange for asset in assets],
+                symbol=[asset.symbol for asset in assets],
+                data_frequency=data_frequency,
+            )
+
+        return start, end
+
+    def prepare_chunks(self, assets, data_frequency, start_dt, end_dt):
+        """
+        Split a price data request into chunks corresponding to individual
+        bundles.
+
+        Parameters
+        ----------
+        assets: list[TradingPair]
+        data_frequency: str
+        start_dt: datetime
+        end_dt: datetime
+
+        Returns
+        -------
+        dict[TradingPair, list[dict(str, Object]]]
+
+        """
+        get_start_end = get_month_start_end \
+            if data_frequency == 'minute' else get_year_start_end
+
+        # Get a reader for the main bundle to verify if data exists
+        reader = self.get_reader(data_frequency)
+
+        chunks = dict()
+        for asset in assets:
+            try:
+                # Checking if the the asset has price data in the specified
+                # date range
+                adj_start, adj_end = self.get_adj_dates(
+                    start_dt, end_dt, [asset], data_frequency
+                )
+
+            except NoDataAvailableOnExchange as e:
+                # If not, we continue to the next asset
+                log.debug('skipping {}: {}'.format(asset.symbol, e))
+                continue
+
+            dates = pd.date_range(
+                start=get_period_label(adj_start, data_frequency),
+                end=get_period_label(adj_end, data_frequency),
+                freq='MS' if data_frequency == 'minute' else 'AS',
+                tz=UTC
+            )
+
+            # Adjusting the last date of the range to avoid
+            # going over the asset's trading bounds
+            dates.values[0] = adj_start
+            dates.values[-1] = adj_end
+
+            chunks[asset] = []
+            for index, dt in enumerate(dates):
+                period_start, period_end = get_start_end(
+                    dt=dt,
+                    first_day=dt if index == 0 else None,
+                    last_day=dt if index == len(dates) - 1 else None
+                )
+
+                # Currencies don't always start trading at midnight.
+                # Checking the last minute of the day instead.
+                range_start = period_start.replace(hour=23, minute=59) \
+                    if data_frequency == 'minute' else period_start
+
+                # Checking if the data already exists in the bundle
+                # for the date range of the chunk. If not, we create
+                # a chunk for ingestion.
+                has_data = range_in_bundle(
+                    asset, range_start, period_end, reader
+                )
+                if not has_data:
+                    period = get_period_label(dt, data_frequency)
+                    chunk = dict(
+                        asset=asset,
+                        period=period,
+                    )
+                    chunks[asset].append(chunk)
+
+            # We sort the chunks by end date to ingest most recent data first
+            chunks[asset].sort(
+                key=lambda chunk: pd.to_datetime(chunk['period'])
+            )
+
+        return chunks
+
+    def ingest_assets(self, assets, data_frequency, start_dt=None, end_dt=None,
+                      show_progress=False, asset_chunks=False):
+        """
+        Determine if data is missing from the bundle and attempt to ingest it.
+
+        Parameters
+        ----------
+        assets: list[TradingPair]
+        data_frequency: str
+        start_dt: datetime
+        end_dt: datetime
+        show_progress: bool
+        asset_chunks: bool
+
+        """
+        if start_dt is None:
+            start_dt = self.calendar.first_session
+
+        if end_dt is None:
+            end_dt = pd.Timestamp.utcnow()
+
+        get_start_end = get_month_start_end \
+            if data_frequency == 'minute' else get_year_start_end
+
+        # Assign the first and last day of the period
+        start_dt, _ = get_start_end(start_dt)
+        _, end_dt = get_start_end(end_dt)
+
+        chunks = self.prepare_chunks(
+            assets=assets,
+            data_frequency=data_frequency,
+            start_dt=start_dt,
+            end_dt=end_dt
+        )
+
+        # This is the common writer for the entire exchange bundle
+        # we want to give an end_date far in time
+        writer = self.get_writer(start_dt, end_dt, data_frequency)
+        if asset_chunks:
+            for asset in chunks:
+                with maybe_show_progress(
+                        chunks[asset],
+                        show_progress,
+                        label='Ingesting {frequency} price data for '
+                              '{symbol} on {exchange}'.format(
+                            exchange=self.exchange.name,
+                            frequency=data_frequency,
+                            symbol=asset.symbol
+                        )) as it:
+                    for chunk in it:
+                        self.ingest_ctable(
+                            asset=chunk['asset'],
+                            data_frequency=data_frequency,
+                            period=chunk['period'],
+                            writer=writer,
+                            empty_rows_behavior='strip',
+                            cleanup=True
+                        )
+        else:
+            all_chunks = list(chain.from_iterable(itervalues(chunks)))
+
+            # We sort the chunks by end date to ingest most recent data first
+            all_chunks.sort(
+                key=lambda chunk: pd.to_datetime(chunk['period'])
+            )
+            with maybe_show_progress(
+                    all_chunks,
+                    show_progress,
+                    label='Ingesting {frequency} price data on '
+                          '{exchange}'.format(
+                        exchange=self.exchange.name,
+                        frequency=data_frequency,
+                    )) as it:
+                for chunk in it:
+                    self.ingest_ctable(
+                        asset=chunk['asset'],
+                        data_frequency=data_frequency,
+                        period=chunk['period'],
+                        writer=writer,
+                        empty_rows_behavior='strip',
+                        cleanup=True
+                    )
+
+    def ingest(self, data_frequency, include_symbols=None,
+               exclude_symbols=None, start=None, end=None,
+               show_progress=True, environ=os.environ):
+        """
+        Inject data based on specified parameters.
+
+        Parameters
+        ----------
+        data_frequency: str
+        include_symbols: str
+        exclude_symbols: str
+        start: datetime
+        end: datetime
+        show_progress: bool
+        environ:
+
+        """
+        assets = self.get_assets(include_symbols, exclude_symbols)
+
+        for frequency in data_frequency.split(','):
+            self.ingest_assets(assets, frequency, start, end,
+                               show_progress, True)
+
+    def get_history_window_series_and_load(self,
+                                           assets,
+                                           end_dt,
+                                           bar_count,
+                                           field,
+                                           data_frequency,
+                                           algo_end_dt=None
+                                           ):
+        """
+        Retrieve price data history, ingest missing data.
+
+        Parameters
+        ----------
+        assets: list[TradingPair]
+        end_dt: datetime
+        bar_count: int
+        field: str
+        data_frequency: str
+        algo_end_dt: datetime
+
+        Returns
+        -------
+        Series
+
+        """
+        try:
+            series = self.get_history_window_series(
+                assets=assets,
+                end_dt=end_dt,
+                bar_count=bar_count,
+                field=field,
+                data_frequency=data_frequency
+            )
+            return pd.DataFrame(series)
+
+        except PricingDataNotLoadedError:
+            start_dt = get_start_dt(end_dt, bar_count, data_frequency)
+            log.info(
+                'pricing data for {symbol} not found in range '
+                '{start} to {end}, updating the bundles.'.format(
+                    symbol=[asset.symbol for asset in assets],
+                    start=start_dt,
+                    end=end_dt
+                )
+            )
+            self.ingest_assets(
+                assets=assets,
+                start_dt=start_dt,
+                end_dt=algo_end_dt,
+                data_frequency=data_frequency,
+                show_progress=True,
+                asset_chunks=True
+            )
+            series = self.get_history_window_series(
+                assets=assets,
+                end_dt=end_dt,
+                bar_count=bar_count,
+                field=field,
+                data_frequency=data_frequency,
+                reset_reader=False
+            )
+            return series
+
+    def get_spot_values(self,
+                        assets,
+                        field,
+                        dt,
+                        data_frequency,
+                        reset_reader=False
+                        ):
+        """
+        The spot values for the gives assets, field and date. Reads from
+        the exchange data bundle.
+
+        :param assets:
+        :param field:
+        :param dt:
+        :param data_frequency:
+        :param reset_reader:
+        :return:
+        """
+        values = []
+        try:
+            reader = self.get_reader(data_frequency)
+            if reset_reader:
+                del self._readers[reader._rootdir]
+                reader = self.get_reader(data_frequency)
+
+            for asset in assets:
+                value = reader.get_value(
+                    sid=asset.sid,
+                    dt=dt,
+                    field=field
+                )
+                values.append(value)
+
+            return values
+
+        except Exception:
+            symbols = [asset.symbol for asset in assets]
+            raise PricingDataNotLoadedError(
+                field=field,
+                first_trading_day=min([asset.start_date for asset in assets]),
+                exchange=self.exchange.name,
+                symbols=symbols,
+                symbol_list=','.join(symbols),
+                data_frequency=data_frequency
+            )
+
+    def get_history_window_series(self,
+                                  assets,
+                                  end_dt,
+                                  bar_count,
+                                  field,
+                                  data_frequency,
+                                  reset_reader=False):
+        start_dt = get_start_dt(end_dt, bar_count, data_frequency)
+        start_dt, end_dt = self.get_adj_dates(
+            start_dt, end_dt, assets, data_frequency
+        )
+
+        reader = self.get_reader(data_frequency)
+        if reset_reader:
+            del self._readers[reader._rootdir]
+            reader = self.get_reader(data_frequency)
+
+        if reader is None:
+            symbols = [asset.symbol for asset in assets]
+            raise PricingDataNotLoadedError(
+                field=field,
+                first_trading_day=min([asset.start_date for asset in assets]),
+                exchange=self.exchange.name,
+                symbols=symbols,
+                symbol_list=','.join(symbols),
+                data_frequency=data_frequency
+            )
+
+        for asset in assets:
+            asset_start_dt, asset_end_dt = self.get_adj_dates(
+                start_dt, end_dt, assets, data_frequency
+            )
+
+            in_bundle = range_in_bundle(
+                asset, asset_start_dt, asset_end_dt, reader
+            )
+            if not in_bundle:
+                raise PricingDataNotLoadedError(
+                    field=field,
+                    first_trading_day=asset.start_date,
+                    exchange=self.exchange.name,
+                    symbols=asset.symbol,
+                    symbol_list=asset.symbol,
+                    data_frequency=data_frequency
+                )
+
+        series = dict()
+        try:
+            arrays = reader.load_raw_arrays(
+                sids=[asset.sid for asset in assets],
+                fields=[field],
+                start_dt=start_dt,
+                end_dt=end_dt
+            )
+
+        except Exception:
+            symbols = [asset.symbol.encode('utf-8') for asset in assets]
+            raise PricingDataNotLoadedError(
+                field=field,
+                first_trading_day=min([asset.start_date for asset in assets]),
+                exchange=self.exchange.name,
+                symbols=symbols,
+                symbol_list=','.join(symbols),
+                data_frequency=data_frequency
+            )
+
+        periods = self.get_calendar_periods_range(
+            start_dt, end_dt, data_frequency
+        )
+
+        for asset_index, asset in enumerate(assets):
+            asset_values = arrays[asset_index]
+
+            value_series = pd.Series(asset_values.flatten(), index=periods)
+            series[asset] = value_series
+
+        return series
+
+    def clean(self, data_frequency):
+        """
+        Removing the bundle data from the catalyst folder.
+
+        Parameters
+        ----------
+        data_frequency: str
+
+        """
+        log.debug('cleaning exchange {}, frequency {}'.format(
+            self.exchange.name, data_frequency
+        ))
+        root = get_exchange_folder(self.exchange.name)
+
+        symbols = os.path.join(root, 'symbols.json')
+        if os.path.isfile(symbols):
+            os.remove(symbols)
+
+        temp_bundles = os.path.join(root, 'temp_bundles')
+
+        if os.path.isdir(temp_bundles):
+            log.debug('removing folder and content: {}'.format(temp_bundles))
+            shutil.rmtree(temp_bundles)
+            log.debug('{} removed'.format(temp_bundles))
+
+        frequencies = ['daily', 'minute'] if data_frequency is None \
+            else [data_frequency]
+
+        for frequency in frequencies:
+            label = '{}_bundle'.format(frequency)
+            frequency_bundle = os.path.join(root, label)
+
+            if os.path.isdir(frequency_bundle):
+                log.debug(
+                    'removing folder and content: {}'.format(frequency_bundle)
+                )
+                shutil.rmtree(frequency_bundle)
+                log.debug('{} removed'.format(frequency_bundle))

catalyst/exchange/exchange_data_portal.py

@@ -0,0 +1,401 @@
+import abc
+from time import sleep
+
+import numpy as np
+import pandas as pd
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+
+from catalyst.constants import LOG_LEVEL
+from catalyst.data.data_portal import DataPortal
+from catalyst.exchange.exchange_bundle import ExchangeBundle
+from catalyst.exchange.exchange_errors import (
+    ExchangeRequestError,
+    ExchangeBarDataError,
+    PricingDataNotLoadedError)
+from catalyst.exchange.exchange_utils import get_frequency, resample_history_df
+
+log = Logger('DataPortalExchange', level=LOG_LEVEL)
+
+
+class DataPortalExchangeBase(DataPortal):
+    def __init__(self, *args, **kwargs):
+
+        self.exchanges = kwargs.pop('exchanges', None)
+        # TODO: put somewhere accessible by each algo
+        self.retry_get_history_window = 5
+        self.retry_get_spot_value = 5
+        self.retry_delay = 5
+
+        super(DataPortalExchangeBase, self).__init__(*args, **kwargs)
+
+    def _get_history_window(self,
+                            assets,
+                            end_dt,
+                            bar_count,
+                            frequency,
+                            field,
+                            data_frequency,
+                            ffill=True,
+                            attempt_index=0):
+        try:
+            exchange_assets = dict()
+            for asset in assets:
+                if asset.exchange not in exchange_assets:
+                    exchange_assets[asset.exchange] = list()
+
+                exchange_assets[asset.exchange].append(asset)
+
+            if len(exchange_assets) > 1:
+                df_list = []
+                for exchange_name in exchange_assets:
+                    exchange = self.exchanges[exchange_name]
+                    assets = exchange_assets[exchange_name]
+
+                    df_exchange = self.get_exchange_history_window(
+                        exchange,
+                        assets,
+                        end_dt,
+                        bar_count,
+                        frequency,
+                        field,
+                        data_frequency,
+                        ffill)
+
+                    df_list.append(df_exchange)
+
+                # Merging the values values of each exchange
+                return pd.concat(df_list)
+
+            else:
+                exchange = self.exchanges[list(exchange_assets.keys())[0]]
+                return self.get_exchange_history_window(
+                    exchange,
+                    assets,
+                    end_dt,
+                    bar_count,
+                    frequency,
+                    field,
+                    data_frequency,
+                    ffill)
+
+        except ExchangeRequestError as e:
+            log.warn(
+                'get history attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_get_history_window:
+                sleep(self.retry_delay)
+                return self._get_history_window(assets,
+                                                end_dt,
+                                                bar_count,
+                                                frequency,
+                                                field,
+                                                data_frequency,
+                                                ffill,
+                                                attempt_index + 1)
+            else:
+                raise ExchangeBarDataError(
+                    data_type='history',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def get_history_window(self,
+                           assets,
+                           end_dt,
+                           bar_count,
+                           frequency,
+                           field,
+                           data_frequency=None,
+                           ffill=True):
+
+        if field == 'price':
+            field = 'close'
+
+        return self._get_history_window(assets,
+                                        end_dt,
+                                        bar_count,
+                                        frequency,
+                                        field,
+                                        data_frequency,
+                                        ffill)
+
+    @abc.abstractmethod
+    def get_exchange_history_window(self,
+                                    exchange,
+                                    assets,
+                                    end_dt,
+                                    bar_count,
+                                    frequency,
+                                    field,
+                                    data_frequency,
+                                    ffill=True):
+        pass
+
+    def _get_spot_value(self, assets, field, dt, data_frequency,
+                        attempt_index=0):
+        try:
+            if isinstance(assets, TradingPair):
+                exchange = self.exchanges[assets.exchange]
+                spot_values = self.get_exchange_spot_value(
+                    exchange, [assets], field, dt, data_frequency)
+
+                if not spot_values:
+                    return np.nan
+
+                return spot_values[0]
+
+            else:
+                exchange_assets = dict()
+                for asset in assets:
+                    if asset.exchange not in exchange_assets:
+                        exchange_assets[asset.exchange] = list()
+
+                    exchange_assets[asset.exchange].append(asset)
+
+                if len(list(exchange_assets.keys())) == 1:
+                    exchange = self.exchanges[list(exchange_assets.keys())[0]]
+                    return self.get_exchange_spot_value(
+                        exchange, assets, field, dt, data_frequency)
+
+                else:
+                    spot_values = []
+                    for exchange_name in exchange_assets:
+                        exchange = self.exchanges[exchange_name]
+                        assets = exchange_assets[exchange_name]
+                        exchange_spot_values = self.get_exchange_spot_value(
+                            exchange,
+                            assets,
+                            field,
+                            dt,
+                            data_frequency
+                        )
+                        if len(assets) == 1:
+                            spot_values.append(exchange_spot_values)
+                        else:
+                            spot_values += exchange_spot_values
+
+                    return spot_values
+
+        except ExchangeRequestError as e:
+            log.warn(
+                'get spot value attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_get_spot_value:
+                sleep(self.retry_delay)
+                return self._get_spot_value(assets, field, dt, data_frequency,
+                                            attempt_index + 1)
+            else:
+                raise ExchangeBarDataError(
+                    data_type='spot',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def get_spot_value(self, assets, field, dt, data_frequency):
+        if field == 'price':
+            field = 'close'
+
+        return self._get_spot_value(assets, field, dt, data_frequency)
+
+    @abc.abstractmethod
+    def get_exchange_spot_value(self, exchange, assets, field, dt,
+                                data_frequency):
+        return
+
+    def get_adjusted_value(self, asset, field, dt,
+                           perspective_dt,
+                           data_frequency,
+                           spot_value=None):
+        # TODO: does this pertain to cryptocurrencies?
+        log.warn('get_adjusted_value is not implemented yet!')
+        return spot_value
+
+
+class DataPortalExchangeLive(DataPortalExchangeBase):
+    def __init__(self, *args, **kwargs):
+        super(DataPortalExchangeLive, self).__init__(*args, **kwargs)
+
+    def get_exchange_history_window(self,
+                                    exchange,
+                                    assets,
+                                    end_dt,
+                                    bar_count,
+                                    frequency,
+                                    field,
+                                    data_frequency,
+                                    ffill=True):
+        """
+        Fetching price history window from the exchange.
+
+        Parameters
+        ----------
+        exchange: Exchange
+        assets: list[TradingPair]
+        end_dt: datetime
+        bar_count: int
+        frequency: str
+        field: str
+        data_frequency: str
+        ffill: bool
+
+        Returns
+        -------
+        DataFrame
+
+        """
+        df = exchange.get_history_window(
+            assets,
+            end_dt,
+            bar_count,
+            frequency,
+            field,
+            data_frequency,
+            ffill)
+        return df
+
+    def get_exchange_spot_value(self, exchange, assets, field, dt,
+                                data_frequency):
+        """
+        A spot value for the exchange.
+
+        Parameters
+        ----------
+        exchange: Exchange
+        assets: list[TradingPair]
+        field: str
+        dt: datetime
+        data_frequency: str
+
+        Returns
+        -------
+        float
+
+        """
+        exchange_spot_values = exchange.get_spot_value(
+            assets, field, dt, data_frequency)
+
+        return exchange_spot_values
+
+
+class DataPortalExchangeBacktest(DataPortalExchangeBase):
+    def __init__(self, *args, **kwargs):
+        super(DataPortalExchangeBacktest, self).__init__(*args, **kwargs)
+
+        self.exchange_bundles = dict()
+
+        self.history_loaders = dict()
+        self.minute_history_loaders = dict()
+
+        for exchange_name in self.exchanges:
+            exchange = self.exchanges[exchange_name]
+            self.exchange_bundles[exchange_name] = ExchangeBundle(exchange)
+
+    def _get_first_trading_day(self, assets):
+        first_date = None
+        for asset in assets:
+            if first_date is None or asset.start_date > first_date:
+                first_date = asset.start_date
+        return first_date
+
+    def get_exchange_history_window(self,
+                                    exchange,
+                                    assets,
+                                    end_dt,
+                                    bar_count,
+                                    frequency,
+                                    field,
+                                    data_frequency,
+                                    ffill=True):
+        """
+        Fetching price history window from the exchange bundle.
+
+        Parameters
+        ----------
+        exchange: Exchange
+        assets: list[TradingPair]
+        end_dt: datetime
+        bar_count: int
+        frequency: str
+        field: str
+        data_frequency: str
+        ffill: bool
+
+        Returns
+        -------
+        DataFrame
+
+        """
+        bundle = self.exchange_bundles[exchange.name]  # type: ExchangeBundle
+
+        freq, candle_size, unit, adj_data_frequency = get_frequency(
+            frequency, data_frequency
+        )
+        adj_bar_count = candle_size * bar_count
+
+        if data_frequency == 'minute' and adj_data_frequency == 'daily':
+            end_dt = end_dt.floor('1D')
+
+        series = bundle.get_history_window_series_and_load(
+            assets=assets,
+            end_dt=end_dt,
+            bar_count=adj_bar_count,
+            field=field,
+            data_frequency=adj_data_frequency,
+            algo_end_dt=self._last_available_session,
+        )
+
+        df = resample_history_df(pd.DataFrame(series), freq, field)
+        return df
+
+    def get_exchange_spot_value(self,
+                                exchange,
+                                assets,
+                                field,
+                                dt,
+                                data_frequency
+                                ):
+        """
+        A spot value for the exchange bundle. Try to ingest data if not in
+        the bundle.
+
+        Parameters
+        ----------
+        exchange: Exchange
+        assets: list[TradingPair]
+        field: str
+        dt: datetime
+        data_frequency: str
+
+        Returns
+        -------
+        float
+
+        """
+        bundle = self.exchange_bundles[exchange.name]
+        if data_frequency == 'daily':
+            dt = dt.floor('1D')
+        else:
+            dt = dt.floor('1 min')
+
+        try:
+            return bundle.get_spot_values(assets, field, dt, data_frequency)
+
+        except PricingDataNotLoadedError:
+            log.info(
+                'pricing data for {symbol} not found on {dt}'
+                ', updating the bundles.'.format(
+                    symbol=[asset.symbol for asset in assets],
+                    dt=dt
+                )
+            )
+            bundle.ingest_assets(
+                assets=assets,
+                start_dt=self._first_trading_day,
+                end_dt=self._last_available_session,
+                data_frequency=data_frequency,
+                show_progress=True
+            )
+            return bundle.get_spot_values(
+                assets, field, dt, data_frequency, True
+            )

catalyst/exchange/exchange_errors.py

@@ -1,6 +1,24 @@
+import sys
+import traceback
+
 from catalyst.errors import ZiplineError
 
 
+def silent_except_hook(exctype, excvalue, exctraceback):
+    if exctype in [PricingDataBeforeTradingError, PricingDataNotLoadedError,
+                   SymbolNotFoundOnExchange, NoDataAvailableOnExchange,
+                   ExchangeAuthEmpty]:
+        fn = traceback.extract_tb(exctraceback)[-1][0]
+        ln = traceback.extract_tb(exctraceback)[-1][1]
+        print("Error traceback: {1} (line {2})\n"
+              "{0.__name__}:  {3}".format(exctype, fn, ln, excvalue))
+    else:
+        sys.__excepthook__(exctype, excvalue, exctraceback)
+
+
+sys.excepthook = silent_except_hook
+
+
 class ExchangeRequestError(ZiplineError):
     msg = (
         'Request failed: {error}'
@@ -34,6 +52,13 @@ class ExchangeTransactionError(ZiplineError):
     ).strip()
 
 
+class ExchangeNotFoundError(ZiplineError):
+    msg = (
+        'Exchange {exchange_name} not found. Please specify exchanges '
+        'supported by Catalyst and verify spelling for accuracy.'
+    ).strip()
+
+
 class ExchangeAuthNotFound(ZiplineError):
     msg = (
         'Please create an auth.json file containing the api token and key for '
@@ -41,6 +66,13 @@ class ExchangeAuthNotFound(ZiplineError):
     ).strip()
 
 
+class ExchangeAuthEmpty(ZiplineError):
+    msg = (
+        'Please enter your API token key and secret for exchange {exchange} '
+        'in the following file: {filename}'
+    ).strip()
+
+
 class ExchangeSymbolsNotFound(ZiplineError):
     msg = (
         'Unable to download or find a local copy of symbols.json for exchange '
@@ -54,9 +86,24 @@ class AlgoPickleNotFound(ZiplineError):
     ).strip()
 
 
+class InvalidHistoryFrequencyAlias(ZiplineError):
+    msg = (
+        'Invalid frequency alias {freq}. Valid suffixes are M (minute) '
+        'and D (day). For example, these aliases would be valid '
+        '1M, 5M, 1D.'
+    ).strip()
+
+
 class InvalidHistoryFrequencyError(ZiplineError):
     msg = (
-        'History frequency {frequency} not supported by the exchange.'
+        'Frequency {frequency} not supported by the exchange.'
+    ).strip()
+
+
+class MismatchingFrequencyError(ZiplineError):
+    msg = (
+        'Bar aggregate frequency {frequency} not compatible with '
+        'data frequency {data_frequency}.'
     ).strip()
 
 
@@ -87,6 +134,19 @@ class OrderNotFound(ZiplineError):
     ).strip()
 
 
+class OrphanOrderError(ZiplineError):
+    msg = (
+        'Order {order_id} found in exchange {exchange} but not tracked by '
+        'the algorithm.'
+    ).strip()
+
+
+class OrphanOrderReverseError(ZiplineError):
+    msg = (
+        'Order {order_id} tracked by algorithm, but not found in exchange {exchange}.'
+    ).strip()
+
+
 class OrderCancelError(ZiplineError):
     msg = (
         'Unable to cancel order {order_id} on exchange {exchange} {error}.'
@@ -111,3 +171,60 @@ class MismatchingBaseCurrencies(ZiplineError):
         'Unable to trade with base currency {base_currency} when the '
         'algorithm uses {algo_currency}.'
     ).strip()
+
+
+class MismatchingBaseCurrenciesExchanges(ZiplineError):
+    msg = (
+        'Unable to trade with base currency {base_currency} when the '
+        'exchange {exchange_name} users {exchange_currency}.'
+    ).strip()
+
+
+class SymbolNotFoundOnExchange(ZiplineError):
+    """
+    Raised when a symbol() call contains a non-existent symbol.
+    """
+    msg = ('Symbol {symbol} not found on exchange {exchange}. '
+           'Choose from: {supported_symbols}').strip()
+
+
+class BundleNotFoundError(ZiplineError):
+    msg = ('Unable to find bundle data for exchange {exchange} and '
+           'data frequency {data_frequency}.'
+           'Please ingest some price data.'
+           'See `catalyst ingest-exchange --help` for details.').strip()
+
+
+class TempBundleNotFoundError(ZiplineError):
+    msg = ('Temporary bundle not found in: {path}.').strip()
+
+
+class EmptyValuesInBundleError(ZiplineError):
+    msg = ('{name} with end minute {end_minute} has empty rows '
+           'in ranges: {dates}').strip()
+
+
+class PricingDataBeforeTradingError(ZiplineError):
+    msg = ('Pricing data for trading pairs {symbols} on exchange {exchange} '
+           'starts on {first_trading_day}, but you are either trying to trade or '
+           'retrieve pricing data on {dt}. Adjust your dates accordingly.').strip()
+
+
+class PricingDataNotLoadedError(ZiplineError):
+    msg = ('Pricing data {field} for trading pairs {symbols} trading on '
+           'exchange {exchange} since {first_trading_day} is unavailable. '
+           'The bundle data is either out-of-date or has not been loaded yet. '
+           'Please ingest data using the command '
+           '`catalyst ingest-exchange -x {exchange} -f {data_frequency} -i {symbol_list}`. '
+           'See catalyst documentation for details.').strip()
+
+
+class ApiCandlesError(ZiplineError):
+    msg = ('Unable to fetch candles from the remote API: {error}.').strip()
+
+
+class NoDataAvailableOnExchange(ZiplineError):
+    msg = (
+        'Requested data for trading pair {symbol} is not available on exchange {exchange} '
+        'in `{data_frequency}` frequency at this time. '
+        'Check `http://enigma.co/catalyst/status` for market coverage.').strip()

catalyst/exchange/exchange_execution.py

@@ -4,9 +4,16 @@ from catalyst.finance.execution import LimitOrder, StopOrder, StopLimitOrder
 class ExchangeLimitOrder(LimitOrder):
     def get_limit_price(self, is_buy):
         """
-        We may be trading Satoshis with 8 decimals, we cannot round numbers
-        :param is_buy:
-        :return:
+        We may be trading Satoshis with 8 decimals, we cannot round numbers.
+
+        Parameters
+        ----------
+        is_buy: bool
+
+        Returns
+        -------
+        float
+
         """
         return self.limit_price
 
@@ -14,9 +21,16 @@ class ExchangeLimitOrder(LimitOrder):
 class ExchangeStopOrder(StopOrder):
     def get_stop_price(self, is_buy):
         """
-        We may be trading Satoshis with 8 decimals, we cannot round numbers
-        :param is_buy:
-        :return:
+        We may be trading Satoshis with 8 decimals, we cannot round numbers.
+
+        Parameters
+        ----------
+        is_buy: bool
+
+        Returns
+        -------
+        float
+
         """
         return self.stop_price
 
@@ -24,16 +38,30 @@ class ExchangeStopOrder(StopOrder):
 class ExchangeStopLimitOrder(StopLimitOrder):
     def get_limit_price(self, is_buy):
         """
-        We may be trading Satoshis with 8 decimals, we cannot round numbers
-        :param is_buy:
-        :return:
+        We may be trading Satoshis with 8 decimals, we cannot round numbers.
+
+        Parameters
+        ----------
+        is_buy: bool
+
+        Returns
+        -------
+        float
+
         """
         return self.limit_price
 
     def get_stop_price(self, is_buy):
         """
-        We may be trading Satoshis with 8 decimals, we cannot round numbers
-        :param is_buy:
-        :return:
+        We may be trading Satoshis with 8 decimals, we cannot round numbers.
+
+        Parameters
+        ----------
+        is_buy: bool
+
+        Returns
+        -------
+        float
+
         """
         return self.stop_price

catalyst/exchange/exchange_portfolio.py

@@ -1,9 +1,11 @@
 import numpy as np
 from logbook import Logger
 
+from catalyst.constants import LOG_LEVEL
 from catalyst.protocol import Portfolio, Positions, Position
+from catalyst.utils.deprecate import deprecated
 
-log = Logger('ExchangePortfolio')
+log = Logger('ExchangePortfolio', level=LOG_LEVEL)
 
 
 class ExchangePortfolio(Portfolio):
@@ -28,10 +30,15 @@ class ExchangePortfolio(Portfolio):
         self.positions_value = 0.0
         self.open_orders = dict()
 
-    def calculate_pnl(self):
-        log.debug('calculating pnl')
-
     def create_order(self, order):
+        """
+        Create an open order and store in memory.
+
+        Parameters
+        ----------
+        order: Order
+
+        """
         log.debug('creating order {}'.format(order.id))
         self.open_orders[order.id] = order
 
@@ -46,6 +53,18 @@ class ExchangePortfolio(Portfolio):
         log.debug('open order added to portfolio')
 
     def execute_order(self, order, transaction):
+        """
+        Update the open orders and positions to apply an executed order.
+
+        Unlike with backtesting, we do not need to add slippage and fees.
+        The executed price includes transaction fees.
+
+        Parameters
+        ----------
+        order: Order
+        transaction: Transaction
+
+        """
         log.debug('executing order {}'.format(order.id))
         del self.open_orders[order.id]
 
@@ -70,7 +89,41 @@ class ExchangePortfolio(Portfolio):
 
         log.debug('updated portfolio with executed order')
 
+    @deprecated
+    def execute_transaction(self, transaction):
+        # TODO: almost duplicate of execute_order. Not sure why Poloniex needs this.
+        log.debug('executing transaction {}'.format(transaction.order_id))
+
+        order_position = self.positions[transaction.asset] \
+            if transaction.asset in self.positions else None
+
+        if order_position is None:
+            raise ValueError(
+                'Trying to execute transaction for a position not held: %s' % transaction.order_id
+            )
+
+        self.capital_used += transaction.amount * transaction.price
+
+        if transaction.amount > 0:
+            if order_position.cost_basis > 0:
+                order_position.cost_basis = np.average(
+                    [order_position.cost_basis, transaction.price],
+                    weights=[order_position.amount, transaction.amount]
+                )
+            else:
+                order_position.cost_basis = transaction.price
+
+        log.debug('updated portfolio with executed order')
+
     def remove_order(self, order):
+        """
+        Removing an open order.
+
+        Parameters
+        ----------
+        order: Order
+
+        """
         log.info('removing cancelled order {}'.format(order.id))
         del self.open_orders[order.id]
 

catalyst/exchange/exchange_utils.py

@@ -1,20 +1,36 @@
 import json
 import os
 import pickle
-import urllib
+import re
 from datetime import date, datetime
+
 import pandas as pd
+from catalyst.assets._assets import TradingPair
+from six.moves.urllib import request
 
-from catalyst.exchange.exchange_errors import ExchangeAuthNotFound, \
-    ExchangeSymbolsNotFound
-from catalyst.utils.paths import data_root, ensure_directory
+from catalyst.exchange.exchange_errors import ExchangeSymbolsNotFound, \
+    InvalidHistoryFrequencyError, InvalidHistoryFrequencyAlias
+from catalyst.utils.paths import data_root, ensure_directory, \
+    last_modified_time
 
-# TODO: move to aws
-SYMBOLS_URL = 'https://raw.githubusercontent.com/enigmampc/catalyst/' \
-              'master/catalyst/exchange/{exchange}/symbols.json'
+SYMBOLS_URL = 'https://s3.amazonaws.com/enigmaco/catalyst-exchanges/' \
+              '{exchange}/symbols.json'
 
 
 def get_exchange_folder(exchange_name, environ=None):
+    """
+    The root path of an exchange folder.
+
+    Parameters
+    ----------
+    exchange_name: str
+    environ:
+
+    Returns
+    -------
+    str
+
+    """
     if not environ:
         environ = os.environ
 
@@ -25,20 +41,64 @@ def get_exchange_folder(exchange_name, environ=None):
     return exchange_folder
 
 
-def download_exchange_symbols(exchange_name, environ=None):
-    exchange_folder = get_exchange_folder(exchange_name, environ)
-    filename = os.path.join(exchange_folder, 'symbols.json')
+def get_exchange_symbols_filename(exchange_name, environ=None):
+    """
+    The absolute path of the exchange's symbol.json file.
 
+    Parameters
+    ----------
+    exchange_name:
+    environ:
+
+    Returns
+    -------
+    str
+
+    """
+    exchange_folder = get_exchange_folder(exchange_name, environ)
+    return os.path.join(exchange_folder, 'symbols.json')
+
+
+def download_exchange_symbols(exchange_name, environ=None):
+    """
+    Downloads the exchange's symbols.json from the repository.
+
+    Parameters
+    ----------
+    exchange_name: str
+    environ:
+
+    Returns
+    -------
+    str
+
+    """
+    filename = get_exchange_symbols_filename(exchange_name)
     url = SYMBOLS_URL.format(exchange=exchange_name)
-    response = urllib.urlretrieve(url=url, filename=filename)
+    response = request.urlretrieve(url=url, filename=filename)
     return response
 
 
 def get_exchange_symbols(exchange_name, environ=None):
-    exchange_folder = get_exchange_folder(exchange_name, environ)
-    filename = os.path.join(exchange_folder, 'symbols.json')
+    """
+    The de-serialized content of the exchange's symbols.json.
 
-    if not os.path.isfile(filename):
+    Parameters
+    ----------
+    exchange_name: str
+    environ:
+
+    Returns
+    -------
+    Object
+
+    """
+    filename = get_exchange_symbols_filename(exchange_name)
+
+    if not os.path.isfile(filename) or \
+                    pd.Timedelta(pd.Timestamp('now',
+                                              tz='UTC') - last_modified_time(
+                        filename)).days > 1:
         download_exchange_symbols(exchange_name, environ)
 
     if os.path.isfile(filename):
@@ -52,7 +112,37 @@ def get_exchange_symbols(exchange_name, environ=None):
         )
 
 
+def get_symbols_string(assets):
+    """
+    A concatenated string of symbols from a list of assets.
+
+    Parameters
+    ----------
+    assets: list[TradingPair]
+
+    Returns
+    -------
+    str
+
+    """
+    array = [assets] if isinstance(assets, TradingPair) else assets
+    return ', '.join([asset.symbol for asset in array])
+
+
 def get_exchange_auth(exchange_name, environ=None):
+    """
+    The de-serialized contend of the exchange's auth.json file.
+
+    Parameters
+    ----------
+    exchange_name: str
+    environ:
+
+    Returns
+    -------
+    Object
+
+    """
     exchange_folder = get_exchange_folder(exchange_name, environ)
     filename = os.path.join(exchange_folder, 'auth.json')
 
@@ -61,13 +151,27 @@ def get_exchange_auth(exchange_name, environ=None):
             data = json.load(data_file)
             return data
     else:
-        raise ExchangeAuthNotFound(
-            exchange=exchange_name,
-            filename=filename
-        )
+        data = dict(name=exchange_name, key='', secret='')
+        with open(filename, 'w') as f:
+            json.dump(data, f, sort_keys=False, indent=2,
+                      separators=(',', ':'))
+            return data
 
 
 def get_algo_folder(algo_name, environ=None):
+    """
+    The algorithm root folder of the algorithm.
+
+    Parameters
+    ----------
+    algo_name: str
+    environ:
+
+    Returns
+    -------
+    str
+
+    """
     if not environ:
         environ = os.environ
 
@@ -79,6 +183,24 @@ def get_algo_folder(algo_name, environ=None):
 
 
 def get_algo_object(algo_name, key, environ=None, rel_path=None):
+    """
+    The de-serialized object of the algo name and key.
+
+    Parameters
+    ----------
+    algo_name: str
+    key: str
+    environ:
+    rel_path: str
+
+    Returns
+    -------
+    Object
+
+    """
+    if algo_name is None:
+        return None
+
     folder = get_algo_folder(algo_name, environ)
 
     if rel_path is not None:
@@ -97,6 +219,18 @@ def get_algo_object(algo_name, key, environ=None, rel_path=None):
 
 
 def save_algo_object(algo_name, key, obj, environ=None, rel_path=None):
+    """
+    Serialize and save an object by algo name and key.
+
+    Parameters
+    ----------
+    algo_name: str
+    key: str
+    obj: Object
+    environ:
+    rel_path: str
+
+    """
     folder = get_algo_folder(algo_name, environ)
 
     if rel_path is not None:
@@ -109,16 +243,22 @@ def save_algo_object(algo_name, key, obj, environ=None, rel_path=None):
         pickle.dump(obj, handle, protocol=pickle.HIGHEST_PROTOCOL)
 
 
-def append_algo_object(algo_name, key, obj, environ=None):
-    algo_folder = get_algo_folder(algo_name, environ)
-    filename = os.path.join(algo_folder, key + '.p')
-
-    mode = 'a+b' if os.path.isfile(filename) else 'wb'
-    with open(filename, mode) as handle:
-        pickle.dump(obj, handle, protocol=pickle.HIGHEST_PROTOCOL)
-
-
 def get_algo_df(algo_name, key, environ=None, rel_path=None):
+    """
+    The de-serialized DataFrame of an algo name and key.
+
+    Parameters
+    ----------
+    algo_name: str
+    key: str
+    environ:
+    rel_path: str
+
+    Returns
+    -------
+    DataFrame
+
+    """
     folder = get_algo_folder(algo_name, environ)
 
     if rel_path is not None:
@@ -137,19 +277,43 @@ def get_algo_df(algo_name, key, environ=None, rel_path=None):
 
 
 def save_algo_df(algo_name, key, df, environ=None, rel_path=None):
-    folder = get_algo_folder(algo_name, environ)
+    """
+    Serialize to csv and save a DataFrame by algo name and key.
 
+    Parameters
+    ----------
+    algo_name: str
+    key: str
+    df: pd.DataFrame
+    environ:
+    rel_path: str
+
+    """
+    folder = get_algo_folder(algo_name, environ)
     if rel_path is not None:
         folder = os.path.join(folder, rel_path)
         ensure_directory(folder)
 
     filename = os.path.join(folder, key + '.csv')
 
-    with open(filename, 'wb') as handle:
-        df.to_csv(handle)
+    with open(filename, 'wt') as handle:
+        df.to_csv(handle, encoding='UTF_8')
 
 
 def get_exchange_minute_writer_root(exchange_name, environ=None):
+    """
+    The minute writer folder for the exchange.
+
+    Parameters
+    ----------
+    exchange_name: str
+    environ:
+
+    Returns
+    -------
+    BcolzExchangeBarWriter
+
+    """
     exchange_folder = get_exchange_folder(exchange_name, environ)
 
     minute_data_folder = os.path.join(exchange_folder, 'minute_data')
@@ -158,9 +322,163 @@ def get_exchange_minute_writer_root(exchange_name, environ=None):
     return minute_data_folder
 
 
-def perf_serial(obj):
-    """JSON serializer for objects not serializable by default json code"""
+def get_exchange_bundles_folder(exchange_name, environ=None):
+    """
+    The temp folder for bundle downloads by algo name.
 
+    Parameters
+    ----------
+    exchange_name: str
+    environ:
+
+    Returns
+    -------
+    str
+
+    """
+    exchange_folder = get_exchange_folder(exchange_name, environ)
+
+    temp_bundles = os.path.join(exchange_folder, 'temp_bundles')
+    ensure_directory(temp_bundles)
+
+    return temp_bundles
+
+
+def perf_serial(obj):
+    """
+    JSON serializer for objects not serializable by default json code
+
+    Parameters
+    ----------
+    obj: Object
+
+    Returns
+    -------
+    str
+
+    """
     if isinstance(obj, (datetime, date)):
         return obj.isoformat()
+
     raise TypeError("Type %s not serializable" % type(obj))
+
+
+def get_common_assets(exchanges):
+    """
+    The assets available in all specified exchanges.
+
+    Parameters
+    ----------
+    exchanges: list[Exchange]
+
+    Returns
+    -------
+    list[TradingPair]
+
+    """
+    symbols = []
+    for exchange_name in exchanges:
+        s = [asset.symbol for asset in exchanges[exchange_name].get_assets()]
+        symbols.append(s)
+
+    inter_symbols = set.intersection(*map(set, symbols))
+
+    assets = []
+    for symbol in inter_symbols:
+        for exchange_name in exchanges:
+            asset = exchanges[exchange_name].get_asset(symbol)
+            assets.append(asset)
+
+    return assets
+
+
+def get_frequency(freq, data_frequency):
+    """
+    Get the frequency parameters.
+
+    Notes
+    -----
+    We're trying to use Pandas convention for frequency aliases.
+
+    Parameters
+    ----------
+    freq: str
+    data_frequency: str
+
+    Returns
+    -------
+    str, int, str, str
+
+    """
+    if freq == 'minute':
+        unit = 'T'
+        candle_size = 1
+
+    elif freq == 'daily':
+        unit = 'D'
+        candle_size = 1
+
+    else:
+        freq_match = re.match(r'([0-9].*)?(m|M|d|D|h|H|T)', freq, re.M | re.I)
+        if freq_match:
+            candle_size = int(freq_match.group(1)) if freq_match.group(1) \
+                else 1
+            unit = freq_match.group(2)
+
+        else:
+            raise InvalidHistoryFrequencyError(frequency=freq)
+
+    if unit.lower() == 'd':
+        alias = '{}D'.format(candle_size)
+
+        if data_frequency == 'minute':
+            data_frequency = 'daily'
+
+    elif unit.lower() == 'm' or unit == 'T':
+        alias = '{}T'.format(candle_size)
+
+        if data_frequency == 'daily':
+            data_frequency = 'minute'
+
+    # elif unit.lower() == 'h':
+    #     candle_size = candle_size * 60
+    #
+    #     alias = '{}T'.format(candle_size)
+    #     if data_frequency == 'daily':
+    #         data_frequency = 'minute'
+
+    else:
+        raise InvalidHistoryFrequencyAlias(freq=freq)
+
+    return alias, candle_size, unit, data_frequency
+
+
+def resample_history_df(df, freq, field):
+    """
+    Resample the OHCLV DataFrame using the specified frequency.
+
+    Parameters
+    ----------
+    df: DataFrame
+    freq: str
+    field: str
+
+    Returns
+    -------
+    DataFrame
+
+    """
+    if field == 'open':
+        agg = 'first'
+    elif field == 'high':
+        agg = 'max'
+    elif field == 'low':
+        agg = 'min'
+    elif field == 'close':
+        agg = 'last'
+    elif field == 'volume':
+        agg = 'sum'
+    else:
+        raise ValueError('Invalid field.')
+
+    return df.resample(freq).agg(agg)

catalyst/exchange/factory.py

@@ -0,0 +1,43 @@
+from catalyst.exchange.bitfinex.bitfinex import Bitfinex
+from catalyst.exchange.bittrex.bittrex import Bittrex
+from catalyst.exchange.exchange_errors import ExchangeNotFoundError
+from catalyst.exchange.exchange_utils import get_exchange_auth
+from catalyst.exchange.poloniex.poloniex import Poloniex
+
+
+def get_exchange(exchange_name, base_currency=None):
+    exchange_auth = get_exchange_auth(exchange_name)
+    if exchange_name == 'bitfinex':
+        return Bitfinex(
+            key=exchange_auth['key'],
+            secret=exchange_auth['secret'],
+            base_currency=base_currency,
+            portfolio=None
+        )
+
+    elif exchange_name == 'bittrex':
+        return Bittrex(
+            key=exchange_auth['key'],
+            secret=exchange_auth['secret'],
+            base_currency=base_currency,
+            portfolio=None
+        )
+
+    elif exchange_name == 'poloniex':
+        return Poloniex(
+            key=exchange_auth['key'],
+            secret=exchange_auth['secret'],
+            base_currency=base_currency,
+            portfolio=None
+        )
+
+    else:
+        raise ExchangeNotFoundError(exchange_name=exchange_name)
+
+
+def get_exchanges(exchange_names):
+    exchanges = dict()
+    for exchange_name in exchange_names:
+        exchanges[exchange_name] = get_exchange(exchange_name)
+
+    return exchanges

catalyst/exchange/live_graph_clock.py

@@ -1,30 +1,15 @@
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from datetime import timedelta
-
-import matplotlib.dates as mdates
 import pandas as pd
 from catalyst.gens.sim_engine import (
     BAR,
     SESSION_START
 )
 from logbook import Logger
-from matplotlib import pyplot as plt
-from matplotlib import style
 
-log = Logger('LiveGraphClock')
+from catalyst.constants import LOG_LEVEL
+from catalyst.exchange.exchange_errors import \
+    MismatchingBaseCurrenciesExchanges
 
-fmt = mdates.DateFormatter('%Y-%m-%d %H:%M')
+log = Logger('LiveGraphClock', level=LOG_LEVEL)
 
 
 class LiveGraphClock(object):
@@ -35,8 +20,8 @@ class LiveGraphClock(object):
 
     This mixes the clock with a live graph.
 
-    Note
-    ----
+    Notes
+    -----
     This seemingly awkward approach allows us to run the program using a single
     thread. This is important because Matplotlib does not play nice with
     multi-threaded environments. Zipline probably does not either.
@@ -55,11 +40,17 @@ class LiveGraphClock(object):
 
     def __init__(self, sessions, context, time_skew=pd.Timedelta('0s')):
 
+        global mdates, plt  # TODO: Could be cleaner
+        import matplotlib.dates as mdates
+        from matplotlib import pyplot as plt
+        from matplotlib import style
+
         self.sessions = sessions
         self.time_skew = time_skew
         self._last_emit = None
         self._before_trading_start_bar_yielded = True
         self.context = context
+        self.fmt = mdates.DateFormatter('%Y-%m-%d %H:%M')
 
         style.use('dark_background')
 
@@ -91,13 +82,14 @@ class LiveGraphClock(object):
         """
         Trying to assign reasonable parameters to the time axis.
 
-        TODO: room for improvement
+        Parameters
+        ----------
+        ax:
 
-        :param ax:
-        :return:
         """
+        # TODO: room for improvement
         ax.xaxis.set_major_locator(mdates.DayLocator(interval=1))
-        ax.xaxis.set_major_formatter(fmt)
+        ax.xaxis.set_major_formatter(self.fmt)
 
         locator = mdates.HourLocator(interval=4)
         locator.MAXTICKS = 5000
@@ -109,9 +101,21 @@ class LiveGraphClock(object):
         ax.grid(True)
 
     def set_legend(self, ax):
+        """
+        Set legend on the chart.
+
+        Parameters
+        ----------
+        ax
+
+        """
         ax.legend(loc='upper left', ncol=1, fontsize=10, numpoints=1)
 
     def draw_pnl(self):
+        """
+        Draw p&l line on the chart.
+
+        """
         ax = self.ax_pnl
         df = self.context.pnl_stats
 
@@ -132,6 +136,10 @@ class LiveGraphClock(object):
         self.format_ax(ax)
 
     def draw_custom_signals(self):
+        """
+        Draw custom signals on the chart.
+
+        """
         ax = self.ax_custom_signals
         df = self.context.custom_signals_stats
 
@@ -150,21 +158,39 @@ class LiveGraphClock(object):
         self.format_ax(ax)
 
     def draw_exposure(self):
+        """
+        Draw exposure line on the chart.
+
+        """
         ax = self.ax_exposure
         context = self.context
         df = context.exposure_stats
 
+        # TODO: list exchanges in graph
+        base_currency = None
+        positions = []
+        for exchange_name in context.exchanges:
+            exchange = context.exchanges[exchange_name]
+
+            if not base_currency:
+                base_currency = exchange.base_currency
+            elif base_currency != exchange.base_currency:
+                raise MismatchingBaseCurrenciesExchanges(
+                    base_currency=base_currency,
+                    exchange_name=exchange.name,
+                    exchange_currency=exchange.base_currency
+                )
+
+            positions += exchange.portfolio.positions
+
         ax.clear()
         ax.set_title('Exposure')
         ax.plot(df.index, df['base_currency'], '-',
                 color='green',
                 linewidth=1.0,
-                label='Base Currency: {}'.format(
-                    context.exchange.base_currency.upper()
-                )
+                label='Base Currency: {}'.format(base_currency.upper())
                 )
 
-        positions = context.exchange.portfolio.positions
         symbols = []
         for position in positions:
             symbols.append(position.symbol)
@@ -172,10 +198,7 @@ class LiveGraphClock(object):
         ax.plot(df.index, df['long_exposure'], '-',
                 color='blue',
                 linewidth=1.0,
-                label='Long Exposure: {}'.format(
-                    ', '.join(symbols).upper()
-                )
-                )
+                label='Long Exposure: {}'.format(', '.join(symbols).upper()))
 
         self.set_legend(ax)
         self.format_ax(ax)

catalyst/exchange/poloniex/poloniex.py

@@ -0,0 +1,651 @@
+import json
+import json
+import time
+from collections import defaultdict
+
+import numpy as np
+import pandas as pd
+import pytz
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+# import six
+from six import iteritems
+
+from catalyst.constants import LOG_LEVEL
+# from websocket import create_connection
+from catalyst.exchange.exchange import Exchange
+from catalyst.exchange.exchange_bundle import ExchangeBundle
+from catalyst.exchange.exchange_errors import (
+    ExchangeRequestError,
+    InvalidHistoryFrequencyError,
+    InvalidOrderStyle, OrphanOrderReverseError)
+from catalyst.exchange.exchange_execution import ExchangeLimitOrder, \
+    ExchangeStopLimitOrder
+from catalyst.exchange.exchange_utils import get_exchange_symbols_filename, \
+    download_exchange_symbols, get_symbols_string
+from catalyst.exchange.poloniex.poloniex_api import Poloniex_api
+from catalyst.finance.order import Order, ORDER_STATUS
+from catalyst.finance.transaction import Transaction
+from catalyst.protocol import Account
+
+log = Logger('Poloniex', level=LOG_LEVEL)
+
+
+class Poloniex(Exchange):
+    def __init__(self, key, secret, base_currency, portfolio=None):
+        self.api = Poloniex_api(key=key, secret=secret)
+        self.name = 'poloniex'
+        self.assets = {}
+        self.load_assets()
+        self.base_currency = base_currency
+        self._portfolio = portfolio
+        self.minute_writer = None
+        self.minute_reader = None
+        self.transactions = defaultdict(list)
+
+        self.num_candles_limit = 2000
+        self.max_requests_per_minute = 60
+        self.request_cpt = dict()
+
+        self.bundle = ExchangeBundle(self)
+
+    def sanitize_curency_symbol(self, exchange_symbol):
+        """
+        Helper method used to build the universal pair.
+        Include any symbol mapping here if appropriate.
+
+        :param exchange_symbol:
+        :return universal_symbol:
+        """
+        return exchange_symbol.lower()
+
+    def _create_order(self, order_status):
+        """
+        Create a Catalyst order object from the Exchange order dictionary
+        :param order_status:
+        :return: Order
+        """
+        # if order_status['is_cancelled']:
+        #    status = ORDER_STATUS.CANCELLED
+        # elif not order_status['is_live']:
+        #    log.info('found executed order {}'.format(order_status))
+        #    status = ORDER_STATUS.FILLED
+        # else:
+        status = ORDER_STATUS.OPEN
+
+        amount = float(order_status['amount'])
+        # filled = float(order_status['executed_amount'])
+        filled = None
+
+        if order_status['type'] == 'sell':
+            amount = -amount
+            # filled = -filled
+
+        price = float(order_status['rate'])
+        order_type = order_status['type']
+
+        stop_price = None
+        limit_price = None
+
+        # TODO: is this comprehensive enough?
+        # if order_type.endswith('limit'):
+        #    limit_price = price
+        # elif order_type.endswith('stop'):
+        #    stop_price = price
+
+        # executed_price = float(order_status['avg_execution_price'])
+        executed_price = price
+
+        # TODO: bitfinex does not specify comission. I could calculate it but not sure if it's worth it.
+        commission = None
+
+        # date = pd.Timestamp.utcfromtimestamp(float(order_status['timestamp']))
+        # date = pytz.utc.localize(date)
+        date = None
+
+        order = Order(
+            dt=date,
+            asset=self.assets[order_status['symbol']],
+            # No such field in Poloniex
+            amount=amount,
+            stop=stop_price,
+            limit=limit_price,
+            filled=filled,
+            id=str(order_status['orderNumber']),
+            commission=commission
+        )
+        order.status = status
+
+        return order, executed_price
+
+    def get_balances(self):
+        balances = self.api.returnbalances()
+        try:
+            log.debug('retrieving wallets balances')
+        except Exception as e:
+            log.debug(e)
+            raise ExchangeRequestError(error=e)
+
+        if 'error' in balances:
+            raise ExchangeRequestError(
+                error='unable to fetch balance {}'.format(balances['error'])
+            )
+
+        std_balances = dict()
+        for (key, value) in iteritems(balances):
+            currency = key.lower()
+            std_balances[currency] = float(value)
+
+        return std_balances
+
+    @property
+    def account(self):
+        account = Account()
+
+        account.settled_cash = None
+        account.accrued_interest = None
+        account.buying_power = None
+        account.equity_with_loan = None
+        account.total_positions_value = None
+        account.total_positions_exposure = None
+        account.regt_equity = None
+        account.regt_margin = None
+        account.initial_margin_requirement = None
+        account.maintenance_margin_requirement = None
+        account.available_funds = None
+        account.excess_liquidity = None
+        account.cushion = None
+        account.day_trades_remaining = None
+        account.leverage = None
+        account.net_leverage = None
+        account.net_liquidation = None
+
+        return account
+
+    @property
+    def time_skew(self):
+        # TODO: research the time skew conditions
+        return pd.Timedelta('0s')
+
+    def get_account(self):
+        # TODO: fetch account data and keep in cache
+        return None
+
+    def get_candles(self, freq, assets, bar_count=None,
+                    start_dt=None, end_dt=None):
+        """
+        Retrieve OHLVC candles from Poloniex
+
+        :param freq:
+        :param assets:
+        :param bar_count:
+        :return:
+
+        Available Frequencies
+        ---------------------
+        '5m', '15m', '30m', '2h', '4h', '1D'
+        """
+
+        if end_dt is None:
+            end_dt = pd.Timestamp.utcnow()
+
+        log.debug(
+            'retrieving {bars} {freq} candles on {exchange} from '
+            '{end_dt} for markets {symbols}, '.format(
+                bars=bar_count,
+                freq=freq,
+                exchange=self.name,
+                end_dt=end_dt,
+                symbols=get_symbols_string(assets)
+            )
+        )
+
+        if freq == '1T' and (bar_count == 1 or bar_count is None):
+            # TODO: use the order book instead
+            # We use the 5m to fetch the last bar
+            frequency = 300
+        elif freq == '5T':
+            frequency = 300
+        elif freq == '15T':
+            frequency = 900
+        elif freq == '30T':
+            frequency = 1800
+        elif freq == '120T':
+            frequency = 7200
+        elif freq == '240T':
+            frequency = 14400
+        elif freq == '1D':
+            frequency = 86400
+        else:
+            # Poloniex does not offer 1m data candles
+            # It is likely to error out there frequently
+            raise InvalidHistoryFrequencyError(frequency=freq)
+
+        # Making sure that assets are iterable
+        asset_list = [assets] if isinstance(assets, TradingPair) else assets
+        ohlc_map = dict()
+
+        for asset in asset_list:
+
+            # TODO: what's wrong with this?
+            # end = int(time.mktime(end_dt.timetuple()))
+            end = int(time.time())
+            if bar_count is None:
+                start = end - 2 * frequency
+            else:
+                start = end - bar_count * frequency
+
+            try:
+                response = self.api.returnchartdata(
+                    self.get_symbol(asset), frequency, start, end
+                )
+            except Exception as e:
+                raise ExchangeRequestError(error=e)
+
+            if 'error' in response:
+                raise ExchangeRequestError(
+                    error='Unable to retrieve candles: {}'.format(
+                        response.content)
+                )
+
+            def ohlc_from_candle(candle):
+                last_traded = pd.Timestamp.utcfromtimestamp(candle['date'])
+                last_traded = last_traded.replace(tzinfo=pytz.UTC)
+
+                ohlc = dict(
+                    open=np.float64(candle['open']),
+                    high=np.float64(candle['high']),
+                    low=np.float64(candle['low']),
+                    close=np.float64(candle['close']),
+                    volume=np.float64(candle['volume']),
+                    price=np.float64(candle['close']),
+                    last_traded=last_traded
+                )
+
+                return ohlc
+
+            if bar_count is None:
+                ohlc_map[asset] = ohlc_from_candle(response[0])
+            else:
+                ohlc_bars = []
+                for candle in response:
+                    ohlc = ohlc_from_candle(candle)
+                    ohlc_bars.append(ohlc)
+                ohlc_map[asset] = ohlc_bars
+
+        return ohlc_map[assets] \
+            if isinstance(assets, TradingPair) else ohlc_map
+
+    def create_order(self, asset, amount, is_buy, style):
+        """
+        Creating order on the exchange.
+
+        :param asset:
+        :param amount:
+        :param is_buy:
+        :param style:
+        :return:
+        """
+        exchange_symbol = self.get_symbol(asset)
+
+        if isinstance(style, ExchangeLimitOrder) or isinstance(style,
+                                                               ExchangeStopLimitOrder):
+            if isinstance(style, ExchangeStopLimitOrder):
+                log.warn('{} will ignore the stop price'.format(self.name))
+
+            price = style.get_limit_price(is_buy)
+
+            try:
+                if (is_buy):
+                    response = self.api.buy(exchange_symbol, amount, price)
+                else:
+                    response = self.api.sell(exchange_symbol, -amount, price)
+            except Exception as e:
+                raise ExchangeRequestError(error=e)
+
+            date = pd.Timestamp.utcnow()
+
+            if ('orderNumber' in response):
+                order_id = str(response['orderNumber'])
+                order = Order(
+                    dt=date,
+                    asset=asset,
+                    amount=amount,
+                    stop=style.get_stop_price(is_buy),
+                    limit=style.get_limit_price(is_buy),
+                    id=order_id
+                )
+                return order
+            else:
+                log.warn(
+                    '{} order failed: {}'.format('buy' if is_buy else 'sell',
+                                                 response['error']))
+                return None
+        else:
+            raise InvalidOrderStyle(exchange=self.name,
+                                    style=style.__class__.__name__)
+
+    def get_open_orders(self, asset='all'):
+        """Retrieve all of the current open orders.
+
+        Parameters
+        ----------
+        asset : Asset
+            If passed and not 'all', return only the open orders for the given
+            asset instead of all open orders.
+
+        Returns
+        -------
+        open_orders : dict[list[Order]] or list[Order]
+            If 'all' is passed this will return a dict mapping Assets
+            to a list containing all the open orders for the asset.
+            If an asset is passed then this will return a list of the open
+            orders for this asset.
+        """
+
+        return self.portfolio.open_orders
+
+        """
+            TODO: Why going to the exchange if we already have this info locally?
+                  And why creating all these Orders if we later discard them?
+        """
+
+        try:
+            if (asset == 'all'):
+                response = self.api.returnopenorders('all')
+            else:
+                response = self.api.returnopenorders(self.get_symbol(asset))
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'error' in response:
+            raise ExchangeRequestError(
+                error='Unable to retrieve open orders: {}'.format(
+                    order_statuses['message'])
+            )
+
+        print(self.portfolio.open_orders)
+
+        # TODO: Need to handle openOrders for 'all'
+        orders = list()
+        for order_status in response:
+            order, executed_price = self._create_order(
+                order_status)  # will Throw error b/c Polo doesn't track order['symbol']
+            if asset is None or asset == order.sid:
+                orders.append(order)
+
+        return orders
+
+    def get_order(self, order_id):
+        """Lookup an order based on the order id returned from one of the
+        order functions.
+
+        Parameters
+        ----------
+        order_id : str
+            The unique identifier for the order.
+
+        Returns
+        -------
+        order : Order
+            The order object.
+        """
+
+        try:
+            order = self._portfolio.open_orders[order_id]
+        except Exception as e:
+            raise OrphanOrderError(order_id=order_id, exchange=self.name)
+
+        return order
+
+        # TODO: Need to decide whether we fetch orders locally or from exchnage
+        # The code below is ignored
+
+        try:
+            response = self.api.returnopenorders(self.get_symbol(order.sid))
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        for o in response:
+            if (int(o['orderNumber']) == int(order_id)):
+                return order
+
+        return None
+
+    def cancel_order(self, order_param):
+        """Cancel an open order.
+
+        Parameters
+        ----------
+        order_param : str or Order
+            The order_id or order object to cancel.
+        """
+
+        if (isinstance(order_param, Order)):
+            order = order_param
+        else:
+            order = self._portfolio.open_orders[order_param]
+
+        try:
+            response = self.api.cancelorder(order.id)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'error' in response:
+            log.info(
+                'Unable to cancel order {order_id} on exchange {exchange} {error}.'.format(
+                    order_id=order.id,
+                    exchange=self.name,
+                    error=response['error']
+                ))
+
+            # raise OrderCancelError(
+            #    order_id=order.id,
+            #    exchange=self.name,
+            #    error=response['error']
+            # )
+
+        self.portfolio.remove_order(order)
+
+    def tickers(self, assets):
+        """
+        Fetch ticket data for assets
+        https://docs.bitfinex.com/v2/reference#rest-public-tickers
+
+        :param assets:
+        :return:
+        """
+        symbols = self.get_symbols(assets)
+
+        log.debug('fetching tickers {}'.format(symbols))
+
+        try:
+            response = self.api.returnticker()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'error' in response:
+            raise ExchangeRequestError(
+                error='Unable to retrieve tickers: {}'.format(
+                    response['error'])
+            )
+
+        ticks = dict()
+
+        for index, symbol in enumerate(symbols):
+            ticks[assets[index]] = dict(
+                timestamp=pd.Timestamp.utcnow(),
+                bid=float(response[symbol]['highestBid']),
+                ask=float(response[symbol]['lowestAsk']),
+                last_price=float(response[symbol]['last']),
+                low=float(response[symbol]['lowestAsk']),
+                # TODO: Polo does not provide low
+                high=float(response[symbol]['highestBid']),
+                # TODO: Polo does not provide high
+                volume=float(response[symbol]['baseVolume']),
+            )
+
+        log.debug('got tickers {}'.format(ticks))
+        return ticks
+
+    def generate_symbols_json(self, filename=None, source_dates=False):
+        symbol_map = {}
+
+        if not source_dates:
+            fn, r = download_exchange_symbols(self.name)
+            with open(fn) as data_file:
+                cached_symbols = json.load(data_file)
+
+        response = self.api.returnticker()
+
+        for exchange_symbol in response:
+            base, market = self.sanitize_curency_symbol(exchange_symbol).split(
+                '_')
+            symbol = '{market}_{base}'.format(market=market, base=base)
+
+            if (source_dates):
+                start_date = self.get_symbol_start_date(exchange_symbol)
+            else:
+                try:
+                    start_date = cached_symbols[exchange_symbol]['start_date']
+                except KeyError as e:
+                    start_date = time.strftime('%Y-%m-%d')
+
+            try:
+                end_daily = cached_symbols[exchange_symbol]['end_daily']
+            except KeyError as e:
+                end_daily = 'N/A'
+
+            try:
+                end_minute = cached_symbols[exchange_symbol]['end_minute']
+            except KeyError as e:
+                end_minute = 'N/A'
+
+            symbol_map[exchange_symbol] = dict(
+                symbol=symbol,
+                start_date=start_date,
+                end_daily=end_daily,
+                end_minute=end_minute,
+            )
+
+        if (filename is None):
+            filename = get_exchange_symbols_filename(self.name)
+
+        with open(filename, 'w') as f:
+            json.dump(symbol_map, f, sort_keys=True, indent=2,
+                      separators=(',', ':'))
+
+    def get_symbol_start_date(self, symbol):
+        try:
+            r = self.api.returnchartdata(symbol, 86400, pd.to_datetime(
+                '2010-1-1').value // 10 ** 9)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        return time.strftime('%Y-%m-%d', time.gmtime(int(r[0]['date'])))
+
+    def check_open_orders(self):
+        """
+        Need to override this function for Poloniex:
+
+        Loop through the list of open orders in the Portfolio object.
+        Check if any transactions have been executed:
+            If so, create a transaction and apply to the Portfolio.
+        Check if the order is still open:
+            If not, remove it from open orders
+
+        :return:
+        transactions: Transaction[]
+        """
+        transactions = list()
+        if self.portfolio.open_orders:
+            for order_id in list(self.portfolio.open_orders):
+
+                order = self._portfolio.open_orders[order_id]
+                log.debug('found open order: {}'.format(order_id))
+
+                try:
+                    order_open = self.get_order(order_id)
+                except Exception as e:
+                    raise ExchangeRequestError(error=e)
+
+                if (order_open):
+                    delta = pd.Timestamp.utcnow() - order.dt
+                    log.info(
+                        'order {order_id} still open after {delta}'.format(
+                            order_id=order_id,
+                            delta=delta)
+                    )
+
+                try:
+                    response = self.api.returnordertrades(order_id)
+                except Exception as e:
+                    raise ExchangeRequestError(error=e)
+
+                if ('error' in response):
+                    if (not order_open):
+                        raise OrphanOrderReverseError(order_id=order_id,
+                                                      exchange=self.name)
+                else:
+                    for tx in response:
+                        """
+                            We maintain a list of dictionaries of transactions that correspond to
+                            partially filled orders, indexed by order_id. Every time we query 
+                            executed transactions from the exchange, we check if we had that 
+                            transaction for that order already. If not, we process it.
+
+                            When an order if fully filled, we flush the dict of transactions  
+                            associated with that order.
+                        """
+                        if (not filter(
+                                lambda item: item['order_id'] == tx['tradeID'],
+                                self.transactions[order_id])):
+                            log.debug(
+                                'Got new transaction for order {}: amount {}, price {}'.format(
+                                    order_id, tx['amount'], tx['rate']))
+                            tx['amount'] = float(tx['amount'])
+                            if (tx['type'] == 'sell'):
+                                tx['amount'] = -tx['amount']
+                            transaction = Transaction(
+                                asset=order.asset,
+                                amount=tx['amount'],
+                                dt=pd.to_datetime(tx['date'], utc=True),
+                                price=float(tx['rate']),
+                                order_id=tx['tradeID'],
+                                # it's a misnomer, but keeping it for compatibility
+                                commission=float(tx['fee'])
+                            )
+                            self.transactions[order_id].append(transaction)
+                            self.portfolio.execute_transaction(transaction)
+                            transactions.append(transaction)
+
+                    if (not order_open):
+                        """
+                            Since transactions have been executed individually
+                            the only thing left to do is remove them from list of open_orders
+                        """
+                        del self.portfolio.open_orders[order_id]
+                        del self.transactions[order_id]
+
+        return transactions
+
+    def get_orderbook(self, asset, order_type='all'):
+        exchange_symbol = asset.exchange_symbol
+        data = self.api.returnOrderBook(market=exchange_symbol)
+
+        result = dict()
+        for order_type in data:
+            # TODO: filter by type
+            if order_type != 'asks' and order_type != 'bids':
+                continue
+
+            result[order_type] = []
+            for entry in data[order_type]:
+                if len(entry) == 2:
+                    result[order_type].append(
+                        dict(
+                            rate=float(entry[0]),
+                            quantity=float(entry[1])
+                        )
+                    )
+        return result

catalyst/exchange/poloniex/poloniex_api.py

@@ -0,0 +1,213 @@
+#!/usr/bin/env python
+import json
+import time
+import hmac
+import hashlib
+
+from six.moves import urllib
+
+# Workaround for backwards compatibility
+# https://stackoverflow.com/questions/3745771/urllib-request-in-python-2-7
+urlopen = urllib.request.urlopen
+
+
+class Poloniex_api(object):
+    def __init__(self, key, secret):
+        self.key = key
+        self.secret = secret
+
+        self.max_requests_per_second = 6
+        self.request_cpt = dict()
+
+        self.public = ['returnTicker', 'return24Volume', 'returnOrderBook',
+                       'returnTradeHistory', 'returnChartData',
+                       'returnCurrencies', 'returnLoanOrders']
+        self.trading = ['returnBalances', 'returnCompleteBalances',
+                        'returnDepositAddresses',
+                        'generateNewAddress', 'returnDepositsWithdrawals',
+                        'returnOpenOrders',
+                        'returnTradeHistory', 'returnOrderTrades',
+                        'buy', 'sell', 'cancelOrder', 'moveOrder',
+                        'withdraw', 'returnFeeInfo',
+                        'returnAvailableAccountBalances',
+                        'returnTradableBalances', 'transferBalance',
+                        'returnMarginAccountSummary', 'marginBuy',
+                        'marginSell',
+                        'getMarginPosition', 'closeMarginPosition',
+                        'createLoanOffer',
+                        'cancelLoanOffer', 'returnOpenLoanOffers',
+                        'returnActiveLoans',
+                        'returnLendingHistory', 'toggleAutoRenew']
+
+    def ask_request(self):
+        """
+        Asks permission to issue a request to the exchange.
+        The primary purpose is to avoid hitting rate limits.
+
+        The application will pause if the maximum requests per minute
+        permitted by the exchange is exceeded.
+
+        :return boolean:
+
+        """
+        now = time.time()
+        if not self.request_cpt:
+            self.request_cpt = dict()
+            self.request_cpt[now] = 0
+            return True
+
+        cpt_date = list(self.request_cpt.keys())[0]
+        cpt = self.request_cpt[cpt_date]
+
+        if now > cpt_date + 1:
+            self.request_cpt = dict()
+            self.request_cpt[now] = 0
+            return True
+
+        if cpt >= self.max_requests_per_second:
+
+            time.sleep(1)
+
+            now = time.time()
+            self.request_cpt = dict()
+            self.request_cpt[now] = 0
+            return True
+        else:
+            self.request_cpt[cpt_date] += 1
+
+    def query(self, method, req={}):
+
+        if method in self.public:
+            url = 'https://poloniex.com/public?command=' + method + '&' + \
+                  urllib.parse.urlencode(req)
+            headers = {}
+            post_data = None
+        elif method in self.trading:
+            url = 'https://poloniex.com/tradingApi'
+            req['command'] = method
+            req['nonce'] = int(time.time() * 1000)
+            post_data = urllib.parse.urlencode(req)
+
+            signature = hmac.new(self.secret.encode('utf-8'),
+                                 post_data.encode('utf-8'),
+                                 hashlib.sha512).hexdigest()
+            headers = {'Sign': signature, 'Key': self.key}
+
+            post_data = post_data.encode('utf-8')
+        else:
+            raise ValueError(
+                'Method "' + method + '" not found in neither the Public API '
+                                      'or Trading API endpoints'
+            )
+
+        self.ask_request()
+        req = urllib.request.Request(
+            url,
+            data=post_data,
+            headers=headers
+        )
+        return json.loads(urlopen(req).read())
+
+    def returnticker(self):
+        return self.query('returnTicker', {})
+
+    def return24volume(self):
+        return self.query('return24Volume', {})
+
+    def returnOrderBook(self, market='all'):
+        return self.query('returnOrderBook', {'currencyPair': market})
+
+    def returntradehistory(self, market, start=None, end=None):
+        if (start is not None and end is not None):
+            return self.query('returntradehistory',
+                              {'currencyPair': market, 'start': start,
+                               'end': end})
+        else:
+            return self.query('returntradehistory', {'currencyPair': market})
+
+    def returnchartdata(self, market, period, start, end=9999999999):
+        return self.query('returnChartData',
+                          {'currencyPair': market, 'period': period,
+                           'start': start, 'end': end})
+
+    def returncurrencies(self):
+        return self.query('returnCurrencies', {})
+
+    def returnloadorders(self, market):
+        return self.query('returnLoanOrders', {'currency': market})
+
+    def returnbalances(self):
+        return self.query('returnBalances')
+
+    def returncompletebalances(self, account):
+        if (account):
+            return self.query('returnCompleteBalances', {'account': account})
+        else:
+            return self.query('returnCompleteBalances')
+
+    def returndepositaddresses(self):
+        return self.query('returnDepositAddresses')
+
+    def generatenewaddress(self, currency):
+        return self.query('generateNewAddress', {'currency': currency})
+
+    def returnDepositsWithdrawals(self, start, end):
+        return self.query('returnDepositsWithdrawals',
+                          {'start': start, 'end': end})
+
+    def returnopenorders(self, market):
+        return self.query('returnOpenOrders', {'currencyPair': market})
+
+    def returntradehistory(self, market):
+        # TODO: optional start and/or end and limit
+        return self.query('returnTradeHistory', {'currencyPair': market})
+
+    def returnordertrades(self, ordernumber):
+        return self.query('returnOrderTrades', {'orderNumber': ordernumber})
+
+    def buy(self, market, amount, rate, fillorkill=0, immediateorcancel=0,
+            postonly=0):
+        if (fillorkill):
+            return self.query('buy', {'currencyPair': market, 'rate': rate,
+                                      'amount': amount,
+                                      'fillOrKill': fillorkill, })
+        elif (immediateorcancel):
+            return self.query('buy', {'currencyPair': market, 'rate': rate,
+                                      'amount': amount,
+                                      'immediateOrCancel': immediateorcancel, })
+        elif (postonly):
+            return self.query('buy', {'currencyPair': market, 'rate': rate,
+                                      'amount': amount,
+                                      'postOnly': postonly, })
+        else:
+            return self.query('buy', {'currencyPair': market, 'rate': rate,
+                                      'amount': amount, })
+
+    def sell(self, market, amount, rate, fillorkill=0, immediateorcancel=0,
+             postonly=0):
+        if (fillorkill):
+            return self.query('sell', {'currencyPair': market, 'rate': rate,
+                                       'amount': amount,
+                                       'fillOrKill': fillorkill, })
+        elif (immediateorcancel):
+            return self.query('sell', {'currencyPair': market, 'rate': rate,
+                                       'amount': amount,
+                                       'immediateOrCancel': immediateorcancel, })
+        elif (postonly):
+            return self.query('sell', {'currencyPair': market, 'rate': rate,
+                                       'amount': amount,
+                                       'postOnly': postonly, })
+        else:
+            return self.query('sell', {'currencyPair': market, 'rate': rate,
+                                       'amount': amount, })
+
+    def cancelorder(self, ordernumber):
+        return self.query('cancelOrder', {'orderNumber': ordernumber})
+
+    def withdraw(self, currency, quantity, address):
+        return self.query('withdraw',
+                          {'currency': currency, 'amount': quantity,
+                           'address': address})
+
+    def returnfeeinfo(self):
+        return self.query('returnFeeInfo')

catalyst/exchange/simple_clock.py

@@ -16,13 +16,13 @@ from time import sleep
 import pandas as pd
 from catalyst.gens.sim_engine import (
     BAR,
-    SESSION_START,
-    MINUTE_END,
-    SESSION_END
+    SESSION_START
 )
 from logbook import Logger
 
-log = Logger('ExchangeClock')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('ExchangeClock', level=LOG_LEVEL)
 
 
 class SimpleClock(object):

catalyst/exchange/stats_utils.py

@@ -1,14 +1,73 @@
+import numpy as np
 import pandas as pd
 
 
-def get_pretty_stats(stats_df, num_rows=10):
+def crossover(source, target):
+    """
+    The `x`-series is defined as having crossed over `y`-series if the value
+    of `x` is greater than the value of `y` and the value of `x` was less than
+    the value of `y` on the bar immediately preceding the current bar.
+
+    Parameters
+    ----------
+    source: Series
+    target: Series
+
+    Returns
+    -------
+    bool
+
+    """
+    if source[-1] is np.nan or source[-2] is np.nan \
+            or target[-1] is np.nan or target[-2] is np.nan:
+        return False
+
+    if source[-1] > target[-1] and source[-2] < target[-2]:
+        return True
+    else:
+        return False
+
+
+def crossunder(source, target):
+    """
+    The `x`-series is defined as having crossed under `y`-series if the value
+    of `x` is less than the value of `y` and the value of `x` was greater than
+    the value of `y` on the bar immediately preceding the current bar.
+
+    Parameters
+    ----------
+    source: Series
+    target: Series
+
+    Returns
+    -------
+    bool
+
+    """
+    if source[-1] is np.nan or source[-2] is np.nan \
+            or target[-1] is np.nan or target[-2] is np.nan:
+        return False
+
+    if source[-1] < target[-1] and source[-2] > target[-2]:
+        return True
+    else:
+        return False
+
+
+def get_pretty_stats(stats_df, recorded_cols=None, num_rows=10):
     """
     Format and print the last few rows of a statistics DataFrame.
     See the pyfolio project for the data structure.
 
-    :param stats_df:
-    :param num_rows:
-    :return:
+    Parameters
+    ----------
+    stats_df: DataFrame
+    num_rows: int
+
+    Returns
+    -------
+    str
+
     """
     stats_df.set_index('period_close', drop=True, inplace=True)
     stats_df.dropna(axis=1, how='all', inplace=True)
@@ -22,6 +81,10 @@ def get_pretty_stats(stats_df, num_rows=10):
                'pnl', 'long_exposure', 'short_exposure', 'orders',
                'transactions', 'positions']
 
+    if recorded_cols is not None:
+        for column in recorded_cols:
+            columns.append(column)
+
     def format_positions(positions):
         parts = []
         for position in positions:
@@ -45,3 +108,24 @@ def get_pretty_stats(stats_df, num_rows=10):
         columns=columns,
         formatters=formatters
     )
+
+
+def df_to_string(df):
+    """
+    Create a formatted str representation of the DataFrame.
+
+    Parameters
+    ----------
+    df: DataFrame
+
+    Returns
+    -------
+    str
+
+    """
+    pd.set_option('display.expand_frame_repr', False)
+    pd.set_option('precision', 8)
+    pd.set_option('display.width', 1000)
+    pd.set_option('display.max_colwidth', 1000)
+
+    return df.to_string()

catalyst/finance/blotter.py

@@ -34,7 +34,9 @@ from catalyst.finance.commission import (
 from catalyst.finance.cancel_policy import NeverCancel
 from catalyst.utils.input_validation import expect_types
 
-log = Logger('Blotter')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('Blotter', level=LOG_LEVEL)
 warning_logger = Logger('AlgoWarning')
 
 

catalyst/finance/controls.py

@@ -24,7 +24,9 @@ from catalyst.errors import (
     TradingControlViolation,
 )
 
-log = logbook.Logger('TradingControl')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('TradingControl', level=LOG_LEVEL)
 
 
 class TradingControl(with_metaclass(abc.ABCMeta)):

catalyst/finance/performance/period.py

@@ -88,7 +88,10 @@ from six import itervalues, iteritems
 
 import catalyst.protocol as zp
 
-log = logbook.Logger('Performance')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Performance', level=LOG_LEVEL)
+
 TRADE_TYPE = zp.DATASOURCE_TYPE.TRADE
 
 

catalyst/finance/performance/position.py

@@ -40,7 +40,9 @@ import logbook
 from catalyst.assets import Future, Asset
 from catalyst.utils.input_validation import expect_types
 
-log = logbook.Logger('Performance')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Performance', level=LOG_LEVEL)
 
 
 class Position(object):

catalyst/finance/performance/position_tracker.py

@@ -32,7 +32,9 @@ from catalyst.assets import (
 )
 from . position import positiondict
 
-log = logbook.Logger('Performance')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Performance', level=LOG_LEVEL)
 
 
 PositionStats = namedtuple('PositionStats',

catalyst/finance/performance/tracker.py

@@ -70,7 +70,9 @@ import catalyst.finance.risk as risk
 
 from . position_tracker import PositionTracker
 
-log = logbook.Logger('Performance')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Performance', level=LOG_LEVEL)
 
 
 class PerformanceTracker(object):
@@ -111,27 +113,11 @@ class PerformanceTracker(object):
                     self.treasury_curves,
                     self.trading_calendar
                 )
-        elif self.emission_rate == '5-minute':
-            self.all_benchmark_returns = pd.Series(
-                index=pd.date_range(
-                    self.sim_params.first_open,
-                    self.sim_params.last_close,
-                    freq='5min'
-                ),
-            )
-            self.cumulative_risk_metrics = \
-                risk.RiskMetricsCumulative(
-                    self.sim_params,
-                    self.treasury_curves,
-                    self.trading_calendar,
-                    create_first_day_stats=True,
-                )
         elif self.emission_rate == 'minute':
             self.all_benchmark_returns = pd.Series(index=pd.date_range(
                 self.sim_params.first_open, self.sim_params.last_close,
                 freq='Min')
             )
-
             self.cumulative_risk_metrics = \
                 risk.RiskMetricsCumulative(
                     self.sim_params,

catalyst/finance/risk/cumulative.py

@@ -38,7 +38,9 @@ from empyrical import (
     sortino_ratio,
 )
 
-log = logbook.Logger('Risk Cumulative')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Risk Cumulative', level=LOG_LEVEL)
 
 
 choose_treasury = functools.partial(choose_treasury, lambda *args: '10year',

catalyst/finance/risk/period.py

@@ -36,7 +36,9 @@ from empyrical import (
     sortino_ratio
 )
 
-log = logbook.Logger('Risk Period')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Risk Period', level=LOG_LEVEL)
 
 choose_treasury = functools.partial(risk.choose_treasury,
                                     risk.select_treasury_duration)

catalyst/finance/risk/report.py

@@ -63,7 +63,9 @@ from dateutil.relativedelta import relativedelta
 
 from . period import RiskMetricsPeriod
 
-log = logbook.Logger('Risk Report')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Risk Report', level=LOG_LEVEL)
 
 
 class RiskReport(object):

catalyst/finance/risk/risk.py

@@ -61,7 +61,9 @@ Risk Report
 import logbook
 import numpy as np
 
-log = logbook.Logger('Risk')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Risk', level=LOG_LEVEL)
 
 
 TREASURY_DURATIONS = [

catalyst/finance/trading.py

@@ -26,7 +26,9 @@ from catalyst.data.loader import load_market_data
 from catalyst.utils.calendars import get_calendar
 from catalyst.utils.memoize import remember_last
 
-log = logbook.Logger('Trading')
+from catalyst.constants import LOG_LEVEL
+
+log = logbook.Logger('Trading', level=LOG_LEVEL)
 
 
 DEFAULT_CAPITAL_BASE = 1e5

catalyst/gens/sim_engine.pyx

@@ -20,9 +20,7 @@ cimport cython
 from cpython cimport bool
 
 cdef np.int64_t _nanos_in_minute = 60000000000
-cdef np.int64_t _nanos_in_five_minutes = 5 * _nanos_in_minute
 NANOS_IN_MINUTE = _nanos_in_minute
-NANOS_IN_FIVE_MINUTES = _nanos_in_five_minutes
 
 cpdef enum:
     BAR = 0
@@ -117,24 +115,3 @@ cdef class MinuteSimulationClock:
             yield minute, BAR
             if minute_emission:
                 yield minute, MINUTE_END
-
-cdef class FiveMinuteSimulationClock(MinuteSimulationClock):
-    @cython.boundscheck(False)
-    @cython.wraparound(False)
-    cdef dict calc_minutes_by_session(self):
-        cdef dict five_minutes_by_session
-        cdef int session_idx
-        cdef np.int64_t session_nano
-        cdef np.ndarray[np.int64_t, ndim=1] five_minutes_nanos
-
-        five_minutes_by_session = {}
-        for session_idx, session_nano in enumerate(self.sessions_nanos):
-            five_minutes_nanos = np.arange(
-                self.market_opens_nanos[session_idx],
-                self.market_closes_nanos[session_idx],
-                _nanos_in_five_minutes
-            )
-            five_minutes_by_session[session_nano] = pd.to_datetime(
-                five_minutes_nanos, utc=True, box=True
-            )
-        return five_minutes_by_session

catalyst/gens/tradesimulation.py

@@ -27,14 +27,15 @@ from catalyst.gens.sim_engine import (
     BEFORE_TRADING_START_BAR
 )
 
-log = Logger('Trade Simulation')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('Trade Simulation', level=LOG_LEVEL)
 
 
 class AlgorithmSimulator(object):
 
     EMISSION_TO_PERF_KEY_MAP = {
         'minute': 'minute_perf',
-        '5-minute': '5_minute_perf',
         'daily': 'daily_perf'
     }
 
@@ -202,7 +203,7 @@ class AlgorithmSimulator(object):
             stack.enter_context(self.processor)
             stack.enter_context(ZiplineAPI(self.algo))
 
-            if algo.data_frequency in set(('minute', '5-minute')):
+            if algo.data_frequency == 'minute':
                 def execute_order_cancellation_policy():
                     algo.blotter.execute_cancel_policy(SESSION_END)
 

catalyst/pipeline/loaders/crypto_pricing_loader.py

@@ -41,10 +41,6 @@ class CryptoPricingLoader(PipelineLoader):
             reader = bundle.daily_bar_reader
             all_sessions = cal.all_sessions
 
-        elif data_frequency == '5-minute':
-            reader = bundle.five_minute_bar_reader
-            all_sessions = cal.all_five_minutes
-
         elif data_frequency == 'minute':
             reader = bundle.minute_bar_reader
             all_sessions = cal.all_minutes

catalyst/pipeline/loaders/equity_pricing_loader.py

@@ -40,8 +40,6 @@ class USEquityPricingLoader(PipelineLoader):
 
         if data_frequency == 'daily':
             reader = bundle.daily_bar_reader
-        elif data_frequency == '5-minute':
-            reader = bundle.five_minute_bar_reader
         elif daily_bar_reader == 'minute':
             reader = bundle.minute_bar_reader
         else:
@@ -53,9 +51,6 @@ class USEquityPricingLoader(PipelineLoader):
 
         if data_frequency == 'daily':
             all_sessions = cal.all_sessions
-        elif data_frequency == '5-minute':
-            reader = bundle.five_minute_bar_reader
-            all_sessions = cal.all_five_minutes
         elif daily_bar_reader == 'minute':
             reader = bundle.minute_bar_reader
             all_sessions = cal.all_minutes

catalyst/sources/benchmark_source.py

@@ -65,19 +65,6 @@ class BenchmarkSource(object):
                 )
 
                 self._precalculated_series = minute_series
-            elif self.emission_rate == '5-minute':
-                five_minutes = \
-                    trading_calendar.five_minutes_for_sessions_in_range(
-                        sessions[0],
-                        sessions[-1],
-                    )
-
-                five_minute_series = daily_series.reindex(
-                    index=five_minutes,
-                    method='ffill',
-                )
-                
-                self._precalculated_series = five_minute_series
             else:
                 self._precalculated_series = daily_series
         else:
@@ -85,7 +72,13 @@ class BenchmarkSource(object):
                             "benchmark_returns.")
 
     def get_value(self, dt):
-        return self._precalculated_series.loc[dt]
+        try:
+            series = self._precalculated_series
+            value = series.loc[dt]
+            return value
+        except Exception:
+            # TODO: workaround, find permanent fix
+            return 0
 
     def get_range(self, start_dt, end_dt):
         return self._precalculated_series.loc[start_dt:end_dt]
@@ -168,21 +161,6 @@ class BenchmarkSource(object):
                 ffill=True
             )[asset]
 
-            return benchmark_series.pct_change()[1:]
-        elif self.emission_rate == '5-minute':
-            five_minutes = trading_calendar.five_minutes_for_sessions_in_range(
-                self.sessions[0], self.sessions[-1]
-            )
-            benchmark_series = data_portal.get_history_window(
-                [asset],
-                five_minutes[-1],
-                bar_count=len(five_minutes) + 1,
-                frequency='5m',
-                field='price',
-                data_frequency=self.emission_rate,
-                ffill=True,
-            )[asset]
-
             return benchmark_series.pct_change()[1:]
         else:
             start_date = asset.start_date

catalyst/sources/requests_csv.py

@@ -23,7 +23,9 @@ from catalyst.protocol import (
 )
 from catalyst.assets import Equity
 
-logger = Logger('Requests Source Logger')
+from catalyst.constants import LOG_LEVEL
+
+logger = Logger('Requests Source Logger', level=LOG_LEVEL)
 
 
 def roll_dts_to_midnight(dts, trading_day):

catalyst/support/issue_44.py

@@ -0,0 +1,109 @@
+import pandas as pd
+from catalyst import run_algorithm
+from catalyst.exchange.exchange_utils import get_exchange_symbols
+
+from catalyst.api import (
+    symbols,
+)
+
+
+def initialize(context):
+    context.i = -1
+    context.base_currency = 'btc'
+
+
+def handle_data(context, data):
+    lookback = 60 * 24 * 7  # (minutes, hours, days)
+    context.i += 1
+    if context.i < lookback:
+        return
+
+    today = context.blotter.current_dt.strftime('%Y-%m-%d %H:%M:%S')
+
+    try:
+        # update universe everyday
+        new_day = 60 * 24
+        if not context.i % new_day:
+            context.universe = universe(context, today)
+
+        # get data every 30 minutes
+        minutes = 30
+        if not context.i % minutes and context.universe:
+            for coin in context.coins:
+                pair = str(coin.symbol)
+
+                # ohlcv data
+                open = data.history(coin, 'open', lookback,
+                                    '1m').ffill().bfill().resample(
+                    '30T').first()
+                high = data.history(coin, 'high', lookback,
+                                    '1m').ffill().bfill().resample('30T').max()
+                low = data.history(coin, 'low', lookback,
+                                   '1m').ffill().bfill().resample('30T').min()
+                close = data.history(coin, 'price', lookback,
+                                     '1m').ffill().bfill().resample(
+                    '30T').last()
+                volume = data.history(coin, 'volume', lookback,
+                                      '1m').ffill().bfill().resample(
+                    '30T').sum()
+
+                print(today, pair, close[-1])
+
+    except Exception as e:
+        print(e)
+
+
+def analyze(context=None, results=None):
+    pass
+
+
+def universe(context, today):
+    json_symbols = get_exchange_symbols('poloniex')
+    poloniex_universe_df = pd.DataFrame.from_dict(
+        json_symbols).transpose().astype(str)
+    poloniex_universe_df['base_currency'] = poloniex_universe_df.apply(
+        lambda row: row.symbol.split('_')[1],
+        axis=1)
+    poloniex_universe_df['market_currency'] = poloniex_universe_df.apply(
+        lambda row: row.symbol.split('_')[0],
+        axis=1)
+    poloniex_universe_df = poloniex_universe_df[
+        poloniex_universe_df['base_currency'] == context.base_currency]
+    poloniex_universe_df = poloniex_universe_df[
+        poloniex_universe_df.symbol != 'gas_btc']
+
+    # Markets currently not working on Catalyst 0.3.1
+    # 2017-01-01
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'bcn_btc']
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'burst_btc']
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'dgb_btc']
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'doge_btc']
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'emc2_btc']
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'pink_btc']
+    # poloniex_universe_df = poloniex_universe_df[poloniex_universe_df.symbol != 'sc_btc']
+    print(poloniex_universe_df.head())
+
+    date = str(today).split(' ')[0]
+
+    poloniex_universe_df = poloniex_universe_df[
+        poloniex_universe_df.start_date < date]
+    context.coins = symbols(*poloniex_universe_df.symbol)
+    print(len(poloniex_universe_df))
+    return poloniex_universe_df.symbol.tolist()
+
+
+if __name__ == '__main__':
+    start_date = pd.to_datetime('2017-01-01', utc=True)
+    end_date = pd.to_datetime('2017-10-15', utc=True)
+
+    performance = run_algorithm(start=start_date, end=end_date,
+                                capital_base=10000.0,
+                                initialize=initialize,
+                                handle_data=handle_data,
+                                analyze=analyze,
+                                exchange_name='poloniex',
+                                data_frequency='minute',
+                                base_currency='btc',
+                                live=False,
+                                live_graph=False,
+                                algo_namespace='test')

catalyst/support/issue_47.py

@@ -0,0 +1,140 @@
+"""
+Requires Catalyst version 0.3.0 or above
+Tested on Catalyst version 0.3.2
+
+These example aims to provide and easy way for users to learn how to collect data from the different exchanges.
+You simply need to specify the exchange and the market that you want to focus on.
+You will all see how to create a universe and filter it base on the exchange and the market you desire.
+
+The example prints out the closing price of all the pairs for a given market-exchange every 30 minutes.
+The example also contains the ohlcv minute data for the past seven days which could be used to create indicators
+Use this as the backbone to create your own trading strategies.
+
+Variables lookback date and date are used to ensure data for a coin existed on the lookback period specified.
+"""
+
+import numpy as np
+import pandas as pd
+from datetime import timedelta
+from catalyst import run_algorithm
+from catalyst.exchange.exchange_utils import get_exchange_symbols
+
+from catalyst.api import (
+    symbols,
+)
+
+
+def initialize(context):
+    context.i = -1  # counts the minutes
+    context.exchange = 'poloniex'  # must match the exchange specified in run_algorithm
+    context.base_currency = 'eth'  # must match the base currency specified in run_algorithm
+
+
+def handle_data(context, data):
+    lookback = 60 * 24 * 7  # (minutes, hours, days) of how far to lookback in the data history
+    context.i += 1
+
+    # current date formatted into a string
+    today = context.blotter.current_dt
+    date, time = today.strftime('%Y-%m-%d %H:%M:%S').split(' ')
+    lookback_date = today - timedelta(days=(
+    lookback / (60 * 24)))  # subtract the amount of days specified in lookback
+    lookback_date = lookback_date.strftime('%Y-%m-%d %H:%M:%S').split(' ')[
+        0]  # get only the date as a string
+
+    # update universe everyday
+    new_day = 60 * 24
+    if not context.i % new_day:
+        context.universe = universe(context, lookback_date, date)
+
+    # get data every 30 minutes
+    minutes = 30
+    if not context.i % minutes and context.universe:
+        # we iterate for every pair in the current universe
+        for coin in context.coins:
+            pair = str(coin.symbol)
+
+            # 30 minute interval ohlcv data (the standard data required for candlestick or indicators/signals)
+            # 30T means 30 minutes re-sampling of one minute data. change to your desire time interval.
+            open = fill(data.history(coin, 'open', bar_count=lookback,
+                                     frequency='1m')).resample('30T').first()
+            high = fill(data.history(coin, 'high', bar_count=lookback,
+                                     frequency='1m')).resample('30T').max()
+            low = fill(data.history(coin, 'low', bar_count=lookback,
+                                    frequency='1m')).resample('30T').min()
+            close = fill(data.history(coin, 'price', bar_count=lookback,
+                                      frequency='1m')).resample('30T').last()
+            volume = fill(data.history(coin, 'volume', bar_count=lookback,
+                                       frequency='1m')).resample('30T').sum()
+
+            # close[-1] is the equivalent to current price
+            # displays the minute price for each pair every 30 minutes
+            print(
+            today, pair, open[-1], high[-1], low[-1], close[-1], volume[-1])
+
+            # ----------------------------------------------------------------------------------------------------------
+            # -------------------------------------- Insert Your Strategy Here -----------------------------------------
+            # ----------------------------------------------------------------------------------------------------------
+
+
+def analyze(context=None, results=None):
+    pass
+
+
+# Get the universe for a given exchange and a given base_currency market
+# Example: Poloniex BTC Market
+def universe(context, lookback_date, current_date):
+    json_symbols = get_exchange_symbols(
+        context.exchange)  # get all the pairs for the exchange
+    universe_df = pd.DataFrame.from_dict(json_symbols).transpose().astype(
+        str)  # convert into a dataframe
+    universe_df['base_currency'] = universe_df.apply(
+        lambda row: row.symbol.split('_')[1],
+        axis=1)
+    universe_df['market_currency'] = universe_df.apply(
+        lambda row: row.symbol.split('_')[0],
+        axis=1)
+    # Filter all the exchange pairs to only the ones for a give base currency
+    universe_df = universe_df[
+        universe_df['base_currency'] == context.base_currency]
+
+    # Filter all the pairs to ensure that pair existed in the current date range
+    universe_df = universe_df[universe_df.start_date < lookback_date]
+    universe_df = universe_df[universe_df.end_daily >= current_date]
+    context.coins = symbols(
+        *universe_df.symbol)  # convert all the pairs to symbols
+    print(universe_df.head(), len(universe_df))
+    return universe_df.symbol.tolist()
+
+
+# Replace all NA, NAN or infinite values with its nearest value
+def fill(series):
+    if isinstance(series, pd.Series):
+        return series.replace([np.inf, -np.inf], np.nan).ffill().bfill()
+    elif isinstance(series, np.ndarray):
+        return pd.Series(series).replace([np.inf, -np.inf],
+                                         np.nan).ffill().bfill().values
+    else:
+        return series
+
+
+if __name__ == '__main__':
+    start_date = pd.to_datetime('2017-01-01', utc=True)
+    end_date = pd.to_datetime('2017-10-15', utc=True)
+
+    performance = run_algorithm(start=start_date, end=end_date,
+                                capital_base=10000.0,
+                                initialize=initialize,
+                                handle_data=handle_data,
+                                analyze=analyze,
+                                exchange_name='poloniex',
+                                data_frequency='minute',
+                                base_currency='eth',
+                                live=False,
+                                live_graph=False,
+                                algo_namespace='simple_universe')
+
+"""
+Run in Terminal (inside catalyst environment):
+python simple_universe.py
+"""

catalyst/support/issue_55.py

@@ -0,0 +1,42 @@
+import talib
+import pandas as pd
+
+from catalyst import run_algorithm
+from catalyst.api import symbol
+
+
+def initialize(context):
+    print('initializing')
+    context.asset = symbol('xcp_btc')
+
+
+def handle_data(context, data):
+    print('handling bar: {}'.format(data.current_dt))
+
+    price = data.current(context.asset, 'close')
+    print('got price {price}'.format(price=price))
+
+    try:
+        prices = data.history(
+            context.asset,
+            fields='close',
+            bar_count=1,
+            frequency='1D'
+        )
+        print('got {} price entries\n'.format(len(prices), prices))
+    except Exception as e:
+        print(e)
+
+
+run_algorithm(
+    capital_base=1,
+    start=pd.to_datetime('2015-3-2', utc=True),
+    end=pd.to_datetime('2017-8-31', utc=True),
+    data_frequency='daily',
+    initialize=initialize,
+    handle_data=handle_data,
+    analyze=None,
+    exchange_name='poloniex',
+    algo_namespace='issue_55',
+    base_currency='btc'
+)

catalyst/support/rodrigo_1.py

@@ -0,0 +1,153 @@
+import pandas as pd
+from logbook import Logger, DEBUG
+
+from catalyst import run_algorithm
+from catalyst.api import (schedule_function, order_target_percent, symbol,
+                          date_rules, get_open_orders, cancel_order, record,
+                          set_commission, set_slippage)
+
+log = Logger('rodrigo_1', level=DEBUG)
+"""
+The initialize function sets any data or variables that 
+you'll use in your algorithm. 
+It's only called once at the beginning of your algorithm.
+"""
+
+
+def initialize(context):
+    # Select asset of interest
+    context.asset = symbol('BTC_USD')
+
+    # set_commission(TradingPairFeeSchedule(maker_fee=0.5, taker_fee=0.5))
+    # set_slippage(TradingPairFixedSlippage(spread=0.5))
+    # Set up a rebalance method to run every day
+    schedule_function(rebalance, date_rule=date_rules.every_day())
+
+
+"""
+Rebalance function scheduled to run once per day.
+"""
+
+
+def rebalance(context, data):
+    # To make market decisions, we're calculating the token's
+    # moving average for the last 5 days.
+
+    # We get the price history for the last 5 days.
+    price_history = data.history(context.asset, fields='price', bar_count=5,
+                                 frequency='1d')
+
+    # Then we take an average of those 5 days.
+    average_price = price_history.mean()
+
+    # We also get the coin's current price.
+    price = data.current(context.asset, 'price')
+
+    # Cancel any outstanding orders
+    orders = get_open_orders(context.asset) or []
+    for order in orders:
+        cancel_order(order)
+
+    # If our coin is currently listed on a major exchange
+    if data.can_trade(context.asset):
+        # If the current price is 1% above the 5-day average price,
+        # we open a long position. If the current price is below the
+        # average price, then we want to close our position to 0 shares.
+        if price > (1.01 * average_price):
+            # Place the buy order (positive means buy, negative means sell)
+            order_target_percent(context.asset, .99)
+            log.info("Buying %s" % (context.asset.symbol))
+        elif price < average_price:
+            # Sell all of our shares by setting the target position to zero
+            order_target_percent(context.asset, 0)
+            log.info("Selling %s" % (context.asset.symbol))
+
+    # Use the record() method to track up to five custom signals.
+    # Record Apple's current price and the average price over the last
+    # five days.
+    cash = context.portfolio.cash
+    leverage = context.account.leverage
+
+    record(price=price, average_price=average_price, cash=cash,
+           leverage=leverage)
+
+
+def analyze(context=None, results=None):
+    import matplotlib.pyplot as plt
+
+    # Plot the portfolio and asset data.
+    ax1 = plt.subplot(511)
+    results[['portfolio_value']].plot(ax=ax1)
+    ax1.set_ylabel('Portfolio Value (USD)')
+
+    ax2 = plt.subplot(512, sharex=ax1)
+    ax2.set_ylabel('{asset} (USD)'.format(asset=context.asset))
+    (results[[
+        'price',
+    ]]).plot(ax=ax2)
+
+    trans = results.ix[[t != [] for t in results.transactions]]
+    buys = trans.ix[
+        [t[0]['amount'] > 0 for t in trans.transactions]
+    ]
+    sells = trans.ix[
+        [t[0]['amount'] < 0 for t in trans.transactions]
+    ]
+
+    ax2.plot(
+        buys.index,
+        results.price[buys.index],
+        '^',
+        markersize=10,
+        color='g',
+    )
+    ax2.plot(
+        sells.index,
+        results.price[sells.index],
+        'v',
+        markersize=10,
+        color='r',
+    )
+
+    ax3 = plt.subplot(513, sharex=ax1)
+    results[['leverage']].plot(ax=ax3)
+    ax3.set_ylabel('Leverage ')
+
+    ax4 = plt.subplot(514, sharex=ax1)
+    results[['cash']].plot(ax=ax4)
+    ax4.set_ylabel('Cash (USD)')
+
+    results[[
+        'algorithm',
+        'benchmark',
+    ]] = results[[
+        'algorithm_period_return',
+        'benchmark_period_return',
+    ]]
+
+    ax5 = plt.subplot(515, sharex=ax1)
+    results[[
+        'algorithm',
+        'benchmark',
+    ]].plot(ax=ax5)
+    ax5.set_ylabel('Percent Change')
+
+    plt.legend(loc=3)
+
+    # Show the plot.
+    plt.gcf().set_size_inches(18, 8)
+    plt.show()
+
+
+run_algorithm(
+    capital_base=100000,
+    start=pd.to_datetime('2017-1-1', utc=True),
+    end=pd.to_datetime('2017-10-22', utc=True),
+    data_frequency='minute',
+    initialize=initialize,
+    handle_data=None,
+    analyze=analyze,
+    exchange_name='bitfinex',
+    algo_namespace='rodrigo_1',
+    base_currency='usd'
+)

catalyst/utils/calendars/exchange_calendar_open.py

@@ -31,4 +31,4 @@ class OpenExchangeCalendar(TradingCalendar):
         return DateOffset(days=1)
 
     def __init__(self, *args, **kwargs):
-        super(OpenExchangeCalendar, self).__init__(start=Timestamp('2015-03-01', tz='UTC'), **kwargs)
+        super(OpenExchangeCalendar, self).__init__(start=Timestamp('2015-3-1', tz='UTC'), **kwargs)

catalyst/utils/calendars/trading_calendar.py

@@ -118,9 +118,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
         self._trading_minutes_nanos = self.all_minutes.values.\
             astype(np.int64)
 
-        self._trading_five_minutes_nanos = self.all_five_minutes.values.\
-            astype(np.int64)
-
         self.first_trading_session = _all_days[0]
         self.last_trading_session = _all_days[-1]
 
@@ -182,18 +179,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
         """
         return int(self._minutes_per_session[start_session:end_session].sum())
 
-    @lazyval
-    def _five_minutes_per_session(self):
-        diff = self.schedule.market_close - self.schedule.market_open
-        diff = diff.astype('timedelta64[m]')
-        return (diff + 1) // 5
-
-    def five_minutes_count_for_sessions_in_range(self,
-                                                 start_session,
-                                                 end_session):
-        five_mins = self._five_minutes_per_session[start_session:end_session]
-        return int(five_mins.sum())
-
     @property
     def regular_holidays(self):
         """
@@ -386,10 +371,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
         idx = next_divider_idx(self._trading_minutes_nanos, dt.value)
         return self.all_minutes[idx]
 
-    def next_five_minute(self, dt):
-        idx = next_divider_idx(self._trading_five_minutes_nanos, dt.values)
-        return self.all_five_mintutes[idx]
-
     def previous_minute(self, dt):
         """
         Given a dt, return the previous exchange minute.
@@ -484,12 +465,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
             end_minute=self.schedule.at[session_label, 'market_close'],
         )
 
-    def five_minutes_for_session(self, session_label):
-        return self.five_minutes_in_range(
-            start_five_minute=self.schedule.at[session_label, 'market_open'],
-            end_five_minute=self.schedule.at[session_label, 'market_close'],
-        )
-
     def minutes_window(self, start_dt, count):
         start_dt_nanos = start_dt.value
         all_minutes_nanos = self._trading_minutes_nanos
@@ -591,20 +566,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
 
         return abs(end_idx - start_idx)
 
-    def five_minutes_in_range(self, start_five_minute, end_five_minute):
-        start_idx = searchsorted(self._trading_five_minutes_nanos,
-                                 start_five_minute.value)
-
-        end_idx = searchsorted(self._trading_five_minutes_nanos,
-                               end_five_minute.value)
-
-        if end_five_minute.value == self._trading_five_minutes_nanos[end_idx]:
-            # if the end minute is a market minute, increase by 1
-            end_idx += 1
-
-        return self.all_five_minutes[start_idx:end_idx]
-        
-
     def minutes_in_range(self, start_minute, end_minute):
         """
         Given start and end minutes, return all the calendar minutes
@@ -662,15 +623,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
 
         return self.minutes_in_range(first_minute, last_minute)
 
-    def five_minutes_for_sessions_in_range(self,
-                                           start_session_label,
-                                           end_session_label):
-
-        first_minute, _ = self.open_and_close_for_session(start_session_label)
-        _, last_minute = self.open_and_close_for_session(end_session_label)
-
-        return self.five_minutes_in_range(first_minute, last_minute)
-
     def open_and_close_for_session(self, session_label):
         """
         Returns a tuple of timestamps of the open and close of the session
@@ -777,13 +729,6 @@ class TradingCalendar(with_metaclass(ABCMeta)):
 
         return DatetimeIndex(all_minutes).tz_localize("UTC")
 
-    @lazyval
-    def all_five_minutes(self):
-        """
-        Returns a DatetimeIndex representing all the five minutes in this calendar.
-        """
-        return self._all_minutes_with_interval(5) 
-
     @lazyval
     def all_minutes(self):
         """

catalyst/utils/events.py

@@ -602,7 +602,6 @@ class date_rules(object):
 class time_rules(object):
     market_open = AfterOpen
     market_close = BeforeClose
-    every_5_minutes = Always
     every_minute = Always
 
 

catalyst/utils/paths.py

@@ -126,7 +126,7 @@ def catalyst_root(environ=None):
 
     root = environ.get('ZIPLINE_ROOT', None)
     if root is None:
-        root = expanduser('~/.catalyst')
+        root = os.path.join(expanduser('~'),'.catalyst')
 
     return root
 

catalyst/utils/run_algo.py

@@ -1,16 +1,16 @@
 import os
-import re
-from runpy import run_path
 import sys
 import warnings
-from time import sleep
 from datetime import timedelta
-
-import pandas as pd
+from runpy import run_path
+from time import sleep
 
 import click
+import pandas as pd
 
 from catalyst.exchange.bittrex.bittrex import Bittrex
+from catalyst.exchange.bitfinex.bitfinex import Bitfinex
+from catalyst.exchange.poloniex.poloniex import Poloniex
 
 try:
     from pygments import highlight
@@ -23,34 +23,29 @@ except:
 from toolz import valfilter, concatv
 from functools import partial
 
-from catalyst.algorithm import TradingAlgorithm
-from catalyst.data.bundles.core import load
-from catalyst.data.data_portal import DataPortal
-from catalyst.data.loader import load_crypto_market_data
 from catalyst.finance.trading import TradingEnvironment
-from catalyst.pipeline.data import USEquityPricing, CryptoPricing
-from catalyst.pipeline.loaders import (
-    USEquityPricingLoader,
-    CryptoPricingLoader,
-)
 from catalyst.utils.calendars import get_calendar
 from catalyst.utils.factory import create_simulation_parameters
+from catalyst.data.loader import load_crypto_market_data
 import catalyst.utils.paths as pth
 
-from catalyst.exchange.algorithm_exchange import ExchangeTradingAlgorithm
-from catalyst.exchange.data_portal_exchange import DataPortalExchange
-from catalyst.exchange.bitfinex.bitfinex import Bitfinex
+from catalyst.exchange.exchange_algorithm import ExchangeTradingAlgorithmLive, \
+    ExchangeTradingAlgorithmBacktest
+from catalyst.exchange.exchange_data_portal import DataPortalExchangeLive, \
+    DataPortalExchangeBacktest
 from catalyst.exchange.asset_finder_exchange import AssetFinderExchange
 from catalyst.exchange.exchange_portfolio import ExchangePortfolio
 from catalyst.exchange.exchange_errors import (
-    ExchangeRequestError,
+    ExchangeRequestError, ExchangeAuthEmpty,
     ExchangeRequestErrorTooManyAttempts,
-    BaseCurrencyNotFoundError)
+    BaseCurrencyNotFoundError, ExchangeNotFoundError)
 from catalyst.exchange.exchange_utils import get_exchange_auth, \
-    get_algo_object
+    get_algo_object, get_exchange_folder
 from logbook import Logger
 
-log = Logger('run_algo')
+from catalyst.constants import LOG_LEVEL
+
+log = Logger('run_algo', level=LOG_LEVEL)
 
 
 class _RunAlgoError(click.ClickException, ValueError):
@@ -148,72 +143,96 @@ def _run(handle_data,
     mode = 'live' if live else 'backtest'
     log.info('running algo in {mode} mode'.format(mode=mode))
 
-    if live and exchange is not None:
-        exchange_name = exchange
-        start = pd.Timestamp.utcnow()
-        end = start + timedelta(minutes=1439)
+    exchange_name = exchange
+    if exchange_name is None:
+        raise ValueError('Please specify at least one exchange.')
 
+    exchange_list = [x.strip().lower() for x in exchange.split(',')]
+
+    exchanges = dict()
+    for exchange_name in exchange_list:
+
+        # Looking for the portfolio from the cache first
         portfolio = get_algo_object(
             algo_name=algo_namespace,
             key='portfolio_{}'.format(exchange_name),
             environ=environ
         )
+
         if portfolio is None:
             portfolio = ExchangePortfolio(
                 start_date=pd.Timestamp.utcnow()
             )
 
+        # This corresponds to the json file containing api token info
         exchange_auth = get_exchange_auth(exchange_name)
+
+        if live and (exchange_auth['key'] == '' or exchange_auth['secret'] == ''):
+            raise ExchangeAuthEmpty(
+                    exchange=exchange_name.title(), 
+                    filename=os.path.join(get_exchange_folder(exchange_name, environ), 'auth.json') )
+
         if exchange_name == 'bitfinex':
-            exchange = Bitfinex(
+            exchanges[exchange_name] = Bitfinex(
                 key=exchange_auth['key'],
                 secret=exchange_auth['secret'],
                 base_currency=base_currency,
                 portfolio=portfolio
             )
         elif exchange_name == 'bittrex':
-            exchange = Bittrex(
+            exchanges[exchange_name] = Bittrex(
+                key=exchange_auth['key'],
+                secret=exchange_auth['secret'],
+                base_currency=base_currency,
+                portfolio=portfolio
+            )
+        elif exchange_name == 'poloniex':
+            exchanges[exchange_name] = Poloniex(
                 key=exchange_auth['key'],
                 secret=exchange_auth['secret'],
                 base_currency=base_currency,
                 portfolio=portfolio
             )
         else:
-            raise NotImplementedError(
-                'exchange not supported: %s' % exchange_name)
+            raise ExchangeNotFoundError(exchange_name=exchange_name)
 
     open_calendar = get_calendar('OPEN')
-    sim_params = create_simulation_parameters(
-        start=start,
-        end=end,
-        capital_base=capital_base,
-        data_frequency=data_frequency,
-        emission_rate=data_frequency,
-    )
 
-    if live and exchange is not None:
-        env = TradingEnvironment(
+    env = TradingEnvironment(
+        load=partial(
+            load_crypto_market_data,
             environ=environ,
-            exchange_tz='UTC',
-            asset_db_path=None
-        )
-        env.asset_finder = AssetFinderExchange(exchange)
+            start_dt=start,
+            end_dt=end
+        ),
+        environ=environ,
+        exchange_tz='UTC',
+        asset_db_path=None  # We don't need an asset db, we have exchanges
+    )
+    env.asset_finder = AssetFinderExchange()
+    choose_loader = None  # TODO: use the DataPortal for in the algorithm class for this
 
-        data = DataPortalExchange(
-            exchange=exchange,
+    if live:
+        start = pd.Timestamp.utcnow()
+
+        # TODO: fix the end data.
+        end = start + timedelta(hours=8760)
+
+        data = DataPortalExchangeLive(
+            exchanges=exchanges,
             asset_finder=env.asset_finder,
             trading_calendar=open_calendar,
             first_trading_day=pd.to_datetime('today', utc=True)
         )
-        choose_loader = None
 
-        def fetch_capital_base(attempt_index=0):
+        def fetch_capital_base(exchange, attempt_index=0):
             """
             Fetch the base currency amount required to bootstrap
             the algorithm against the exchange.
 
             The algorithm cannot continue without this value.
 
+            :param exchange: the targeted exchange
             :param attempt_index:
             :return capital_base: the amount of base currency available for
             trading
@@ -224,8 +243,14 @@ def _run(handle_data,
                 balances = exchange.get_balances()
             except ExchangeRequestError as e:
                 if attempt_index < 20:
+                    log.warn(
+                        'could not retrieve balances on {}: {}'.format(
+                            exchange.name, e
+                        )
+                    )
                     sleep(5)
-                    return fetch_capital_base(attempt_index + 1)
+                    return fetch_capital_base(exchange, attempt_index + 1)
+
                 else:
                     raise ExchangeRequestErrorTooManyAttempts(
                         attempts=attempt_index,
@@ -240,110 +265,59 @@ def _run(handle_data,
                     exchange=exchange_name
                 )
 
+        capital_base = 0
+        for exchange_name in exchanges:
+            exchange = exchanges[exchange_name]
+            capital_base += fetch_capital_base(exchange)
+
         sim_params = create_simulation_parameters(
             start=start,
             end=end,
-            capital_base=fetch_capital_base(),
+            capital_base=capital_base,
             emission_rate='minute',
             data_frequency='minute'
         )
 
-    elif bundle is not None:
-        bundles = bundle.split(',')
-
-        def get_trading_env_and_data(bundles):
-            env = data = None
-
-            b = 'poloniex'
-            if len(bundles) == 0:
-                return env, data
-            elif len(bundles) == 1:
-                b = bundles[0]
-
-            bundle_data = load(
-                b,
-                environ,
-                bundle_timestamp,
-            )
-
-            prefix, connstr = re.split(
-                r'sqlite:///',
-                str(bundle_data.asset_finder.engine.url),
-                maxsplit=1,
-            )
-            if prefix:
-                raise ValueError(
-                    "invalid url %r, must begin with 'sqlite:///'" %
-                    str(bundle_data.asset_finder.engine.url),
-                )
-
-            env = TradingEnvironment(
-                load=partial(load_crypto_market_data, bundle=b,
-                             bundle_data=bundle_data, environ=environ),
-                bm_symbol='USDT_BTC',
-                trading_calendar=open_calendar,
-                asset_db_path=connstr,
-                environ=environ,
-            )
-
-            first_trading_day = bundle_data.minute_bar_reader.first_trading_day
-
-            data = DataPortal(
-                env.asset_finder,
-                open_calendar,
-                first_trading_day=first_trading_day,
-                minute_reader=bundle_data.minute_bar_reader,
-                five_minute_reader=bundle_data.five_minute_bar_reader,
-                daily_reader=bundle_data.daily_bar_reader,
-                adjustment_reader=bundle_data.adjustment_reader,
-            )
-
-            return env, data
-
-        def get_loader_for_bundle(b):
-            bundle_data = load(
-                b,
-                environ,
-                bundle_timestamp,
-            )
-
-            if b == 'poloniex':
-                return CryptoPricingLoader(
-                    bundle_data,
-                    data_frequency,
-                    CryptoPricing,
-                )
-            elif b == 'quandl':
-                return USEquityPricingLoader(
-                    bundle_data,
-                    data_frequency,
-                    USEquityPricing,
-                )
-            raise ValueError(
-                "No PipelineLoader registered for bundle %s." % b
-            )
-
-        loaders = [get_loader_for_bundle(b) for b in bundles]
-        env, data = get_trading_env_and_data(bundles)
-
-        def choose_loader(column):
-            for loader in loaders:
-                if column in loader.columns:
-                    return loader
-            raise ValueError(
-                "No PipelineLoader registered for column %s." % column
-            )
+        # TODO: use the constructor instead
+        sim_params._arena = 'live'
 
+        algorithm_class = partial(
+            ExchangeTradingAlgorithmLive,
+            exchanges=exchanges,
+            algo_namespace=algo_namespace,
+            live_graph=live_graph
+        )
     else:
-        env = TradingEnvironment(environ=environ)
-        choose_loader = None
+        # Removed the existing Poloniex fork to keep things simple
+        # We can add back the complexity if required.
 
-    TradingAlgorithmClass = (
-        partial(ExchangeTradingAlgorithm, exchange=exchange,
-                algo_namespace=algo_namespace, live_graph=live_graph)
-        if live and exchange else TradingAlgorithm)
+        # I don't think that we should have arbitrary price data bundles
+        # Instead, we should center this data around exchanges.
+        # We still need to support bundles for other misc data, but we
+        # can handle this later.
 
-    perf = TradingAlgorithmClass(
+        data = DataPortalExchangeBacktest(
+            exchanges=exchanges,
+            asset_finder=None,
+            trading_calendar=open_calendar,
+            first_trading_day=start,
+            last_available_session=end
+        )
+
+        sim_params = create_simulation_parameters(
+            start=start,
+            end=end,
+            capital_base=capital_base,
+            data_frequency=data_frequency,
+            emission_rate=data_frequency,
+        )
+
+        algorithm_class = partial(
+            ExchangeTradingAlgorithmBacktest,
+            exchanges=exchanges
+        )
+
+    perf = algorithm_class(
         namespace=namespace,
         env=env,
         get_pipeline_loader=choose_loader,
@@ -514,6 +488,11 @@ def run_algorithm(initialize,
     """
     load_extensions(default_extension, extensions, strict_extensions, environ)
 
+    # I'm not sure that we need this since the modified DataPortal
+    # does not require extensions to be explicitly loaded.
+
+    # This will be useful for arbitrary non-pricing bundles but we may
+    # need to modify the logic.
     if not live:
         non_none_data = valfilter(bool, {
             'data': data is not None,

docs/CNAME

@@ -1 +1 @@
-www.zipline.io
+enigma-catalyst.readthedocs.io

docs/live-trading-wiki.md

@@ -1,105 +0,0 @@
-<h1>Live Trading</h1>
-This document explains how to get started with live trading.
-
-<h2>Supported Exchanges</h2>
-Catalyst can trade against these exchanges:
-
-* Bitfinex, id=`bitfinex`
-* Bittrex, id=`bittrex`
-
-<h3>Authentication</h3>
-Most exchanges require key/token combination for authentication. By
-convention, Catalyst uses an "auth.json" file to hold this data.
-
-This example illustrates the convention using the Bitfinex exchange.
-Here is how to generate key and secret values for bitfinex:
-https://docs.bitfinex.com/v1/docs/api-access. Most exchanges follow
-a similar process.
-
-The auth.json file:
-```json
-{
-  "name": "bitfinex",
-  "key": "my-key",
-  "secret": "my-secret"
-}
-```
-
-The file goes here:
-```
-~/.catalyst/data/exchanges/bitfinex/auth.json
-```
-
-Note that the 'bitfinex' directory corresponds to the id of the Bitfinex
-exchange as defined in the "Supported Exchanges" section above.
-Attempting to run an algorithm where the targeted exchange is missing
-its "auth.json" file will create the directory structure but result
-in an error.
-
-<h3>Currency Symbols</h3>
-Catalyst introduces a universal convention to reference
-trading pairs and individual currencies. This
-is required to ensure that the `symbol()` api predictably
-returns the correct asset regardless of the targeted exchange.
-
-Exchanges tend to use their own convention to represent currencies
-(e.g. XBT and BTC both represent Bitcoin on different exchanges).
-Trading pairs are also inconsistent. For example, Bitfinex
-puts the market currency before the base currency without a
-separator, Bittrex puts the base currency first and uses a dash
-seperator.
-
-Here is the Catalyst convention:
-
-*[Market Currency]_[Base Currency]* all lowercase.
-
-Currency symbols (e.g. btc, eth, ltc) follow the Bittrex convention.
-
-Here are some examples:
-```python
-# With Bitfinex
-bitcoin_usd_asset = symbol('btc_usd')
-ethereum_bitcoin_asset = symbol('eth_btc')
-
-# With Bittrex
-ethereum_bitcoin_asset = symbol('eth_btc')
-neo_ethereum_asset = symbol('neo_eth)
-```
-
-Note that the trading pairs are always referenced in the same manner.
-However, not all trading pairs are available on all exchanges. An
-error will occur if the specified trading pair is not trading
-on the exchange.
-
-<h2>Trading an Algorithm</h2>
-There is no special convention to follow when writing an
-algorithm for live trading. The same algorithm should work in
-backtest and live execution mode without modification.
-
-What differs are the arguments provided to the catalyst client or
-`run_algorithm()` interface. Here is example:
-
-```python
-run_algorithm(
-    initialize=initialize,
-    handle_data=handle_data,
-    analyze=analyze,
-    exchange_name='bitfinex',
-    live=True,
-    algo_namespace='my_algo_trading_xrp',
-    base_currency='btc'
-)
-```
-
-Here is the breakdown of the new arguments:
-* live: Boolean flag which enables live trading.
-* exchange_name: The name of the targeted exchange
-    (supported values: *bitfinex*, *bittrex*).
-* algo_namespace: A arbitrary label assigned to your algorithm for
-    data storage purposes.
-* base_currency: The base currency used to calculate the
-    statistics of your algorithm. Currently, the base currency of all
-    trading pairs of your algorithm must match this value.
-
-Here is a complete algorithm for reference:
-[Buy Low and Sell High](../catalyst/examples/buy_low_sell_high_live.py)

docs/source/conf.py

@@ -1,7 +1,7 @@
 import sys
 import os
 
-from zipline import __version__ as version
+#from catalyst import __version__ as version
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
@@ -21,14 +21,14 @@ extensions = [
 
 
 extlinks = {
-    'issue': ('https://github.com/quantopian/zipline/issues/%s', '#'),
-    'commit': ('https://github.com/quantopian/zipline/commit/%s', ''),
+    'issue': ('https://github.com/enigmampc/catalyst/issues/%s', '#'),
+    'commit': ('https://github.com/enigmampc/catalyst/commit/%s', ''),
 }
 
 # -- Docstrings ---------------------------------------------------------------
 
-extensions += ['numpydoc']
-numpydoc_show_class_members = False
+#extensions += ['numpydoc']
+#numpydoc_show_class_members = False
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['.templates']
@@ -40,11 +40,12 @@ source_suffix = '.rst'
 master_doc = 'index'
 
 # General information about the project.
-project = u'Zipline'
-copyright = u'2016, Quantopian Inc.'
+project = u'Catalyst'
+copyright = u'2017, Enigma MPC, Inc.'
 
 # The full version, including alpha/beta/rc tags, but excluding the commit hash
-release = version.split('+', 1)[0]
+#release = version.split('+', 1)[0]
+release = '0.3'
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -84,7 +85,7 @@ html_show_sphinx = True
 html_show_copyright = True
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'ziplinedoc'
+htmlhelp_basename = 'catalystdoc'
 
 intersphinx_mapping = {
     'http://docs.python.org/dev': None,
@@ -93,6 +94,6 @@ intersphinx_mapping = {
     'pandas': ('http://pandas.pydata.org/pandas-docs/stable/', None),
 }
 
-doctest_global_setup = "import zipline"
+doctest_global_setup = "import catalyst"
 
 todo_include_todos = True

docs/source/development-guidelines.rst

@@ -1,21 +1,17 @@
 Development Guidelines
 ======================
-This page is intended for developers of Zipline, people who want to contribute to the Zipline codebase or documentation, or people who want to install from source and make local changes to their copy of Zipline.
+This page is intended for developers of Catalyst, people who want to contribute to the Catalyst codebase or documentation, or people who want to install from source and make local changes to their copy of Catalyst.
 
-All contributions, bug reports, bug fixes, documentation improvements, enhancements and ideas are welcome. We `track issues`__ on `GitHub`__ and also have a `mailing list`__ where you can ask questions.
-
-__ https://github.com/quantopian/zipline/issues
-__ https://github.com/
-__ https://groups.google.com/forum/#!forum/zipline
+All contributions, bug reports, bug fixes, documentation improvements, enhancements and ideas are welcome. We `track issues <https://github.com/enigmampc/catalyst/issues>`_ on `GitHub <https://github.com/enigmampc/catalyst>`_ and also have a `discord group <https://discord.gg/SJK32GY>`_ where you can ask questions.
 
 Creating a Development Environment
 ----------------------------------
 
-First, you'll need to clone Zipline by running:
+First, you'll need to clone Catalyst by running:
 
 .. code-block:: bash
 
-   $ git clone git@github.com:your-github-username/zipline.git
+   $ git clone git@github.com:enigmampc/catalyst.git
 
 Then check out to a new branch where you can make your changes:
 
@@ -23,15 +19,13 @@ Then check out to a new branch where you can make your changes:
 		
    $ git checkout -b some-short-descriptive-name
 
-If you don't already have them, you'll need some C library dependencies. You can follow the `install guide`__ to get the appropriate dependencies.
-
-__ install.html
+If you don't already have them, you'll need some C library dependencies. You can follow the `install guide <install.html>`_ to get the appropriate dependencies.
 
 The following section assumes you already have virtualenvwrapper and pip installed on your system. Suggested installation of Python library dependencies used for development:
 
 .. code-block:: bash
 
-   $ mkvirtualenv zipline
+   $ mkvirtualenv catalyst
    $ ./etc/ordered_pip.sh ./etc/requirements.txt
    $ pip install -r ./etc/requirements_dev.txt
    $ pip install -r ./etc/requirements_blaze.txt 
@@ -42,104 +36,39 @@ Finally, you can build the C extensions by running:
 
    $ python setup.py build_ext --inplace
 
-To finish, make sure `tests`__ pass.
+.. To finish, make sure `tests`__ pass.
 
-__ #style-guide-running-tests
+.. __ #style-guide-running-tests
 
-If you get an error running nosetests after setting up a fresh virtualenv, please try running
+.. If you get an error running nosetests after setting up a fresh virtualenv, please try running
 
-.. code-block:: bash
+.. code-block
 
-   # where zipline is the name of your virtualenv
-   $ deactivate zipline
-   $ workon zipline
+..   # where zipline is the name of your virtualenv
+..   $ deactivate zipline
+..   $ workon zipline
 
 
-Development with Docker
+.. Development with Docker
+.. -----------------------
+
+..If you want to work with zipline using a `Docker`__ container, you'll need to build the ``Dockerfile`` in the Zipline root directory, and then build ``Dockerfile-dev``. Instructions for building both containers can be found in ``Dockerfile`` and ``Dockerfile-dev``, respectively.
+
+.. __ https://docs.docker.com/get-started/
+   
+Git Branching Structure
 -----------------------
 
-If you want to work with zipline using a `Docker`__ container, you'll need to build the ``Dockerfile`` in the Zipline root directory, and then build ``Dockerfile-dev``. Instructions for building both containers can be found in ``Dockerfile`` and ``Dockerfile-dev``, respectively.
+If you want to contribute to the codebase of Catalyst, familiarize yourself with our branching structure, a fairly standardized one for that matter, that follows what is documented in the following article: `A successful Git branching model <http://nvie.com/posts/a-successful-git-branching-model/>`_. To contribute, create your local branch and submit a Pull Request (PR) to the **develop** branch.
 
-__ https://docs.docker.com/get-started/
-
-
-Style Guide & Running Tests
----------------------------
-
-We use `flake8`__ for checking style requirements and `nosetests`__ to run Zipline tests. Our `continuous integration`__ tools will run these commands.
-
-__ http://flake8.pycqa.org/en/latest/
-__ http://nose.readthedocs.io/en/latest/
-__ https://en.wikipedia.org/wiki/Continuous_integration
-
-Before submitting patches or pull requests, please ensure that your changes pass when running:
-
-.. code-block:: bash
-
-   $ flake8 zipline tests
-
-In order to run tests locally, you'll need `TA-lib`__, which you can install on Linux by running:
-
-__ https://mrjbq7.github.io/ta-lib/install.html
-
-.. code-block:: bash
-
-   $ wget http://prdownloads.sourceforge.net/ta-lib/ta-lib-0.4.0-src.tar.gz
-   $ tar -xvzf ta-lib-0.4.0-src.tar.gz
-   $ cd ta-lib/
-   $ ./configure --prefix=/usr
-   $ make
-   $ sudo make install
-
-And for ``TA-lib`` on OS X you can just run:
-
-.. code-block:: bash
-
-   $ brew install ta-lib
-
-Then run ``pip install`` TA-lib:
-
-.. code-block:: bash
-
-   $ pip install -r ./etc/requirements_talib.txt
-
-You should now be free to run tests:
-
-.. code-block:: bash
-		
-   $ nosetests
-
-
-Continuous Integration
-----------------------
-
-We use `Travis CI`__ for Linux-64 bit builds and `AppVeyor`__ for Windows-64 bit builds.
-
-.. note::
-
-   We do not currently have CI for OSX-64 bit builds. 32-bit builds may work but are not included in our integration tests.
-
-__ https://travis-ci.org/quantopian/zipline
-__ https://ci.appveyor.com/project/quantopian/zipline
-
-
-Packaging
----------
-To learn about how we build Zipline conda packages, you can read `this`__ section in our release process notes.
-
-__ release-process.html#uploading-conda-packages
+.. image:: https://camo.githubusercontent.com/9bde6fb64a9542a572e0e2017cbb58d9d2c440ac/687474703a2f2f6e7669652e636f6d2f696d672f6769742d6d6f64656c4032782e706e67
 
 Contributing to the Docs
 ------------------------
 
-If you'd like to contribute to the documentation on zipline.io, you can navigate to ``docs/source/`` where each `reStructuredText`__ (``.rst``) file is a separate section there. To add a section, create a new file called ``some-descriptive-name.rst`` and add ``some-descriptive-name`` to ``appendix.rst``. To edit a section, simply open up one of the existing files, make your changes, and save them.
-
-__ https://en.wikipedia.org/wiki/ReStructuredText
-
-We use `Sphinx`__ to generate documentation for Zipline, which you will need to install by running:
-
-__ http://www.sphinx-doc.org/en/stable/
+If you'd like to contribute to the documentation on enigmampc.github.io, you can navigate to ``docs/source/`` where each `reStructuredText <https://en.wikipedia.org/wiki/ReStructuredText>`_ file is a separate section there. To add a section, create a new file called ``some-descriptive-name.rst`` and add ``some-descriptive-name`` to ``index.rst``. To edit a section, simply open up one of the existing files, make your changes, and save them.
 
+We use `Sphinx <http://www.sphinx-doc.org/en/stable/>`_ to generate documentation for Catalyst, which you will need to install by running:
 
 .. code-block:: bash
 
@@ -149,7 +78,7 @@ To build and view the docs locally, run:
 
 .. code-block:: bash
 
-   # assuming you're in the Zipline root directory
+   # assuming you're in the Catalyst root directory
    $ cd docs
    $ make html
    $ {BROWSER} build/html/index.html
@@ -162,7 +91,7 @@ Standard prefixes to start a commit message:
 
 .. code-block:: text
 
-   BLD: change related to building Zipline
+   BLD: change related to building Catalyst
    BUG: bug fix
    DEP: deprecate something, or remove a deprecated object
    DEV: development tool or utility
@@ -172,15 +101,13 @@ Standard prefixes to start a commit message:
    REV: revert an earlier commit
    STY: style fix (whitespace, PEP8, flake8, etc)
    TST: addition or modification of tests
-   REL: related to releasing Zipline
+   REL: related to releasing Catalyst
    PERF: performance enhancements
 
 
 Some commit style guidelines:
 
-Commit lines should be no longer than `72 characters`__. The first line of the commit should include one of the above prefixes. There should be an empty line between the commit subject and the body of the commit. In general, the message should be in the imperative tense. Best practice is to include not only what the change is, but why the change was made.
-
-__ https://git-scm.com/book/en/v2/Distributed-Git-Contributing-to-a-Project
+Commit lines should be no longer than `72 characters <https://git-scm.com/book/en/v2/Distributed-Git-Contributing-to-a-Project>`_. The first line of the commit should include one of the above prefixes. There should be an empty line between the commit subject and the body of the commit. In general, the message should be in the imperative tense. Best practice is to include not only what the change is, but why the change was made.
 
 **Example:**
 
@@ -203,8 +130,6 @@ __ https://git-scm.com/book/en/v2/Distributed-Git-Contributing-to-a-Project
 Formatting Docstrings
 ---------------------
 
-When adding or editing docstrings for classes, functions, etc, we use `numpy`__ as the canonical reference.
-
-__ https://github.com/numpy/numpy/blob/master/doc/HOWTO_DOCUMENT.rst.txt
+When adding or editing docstrings for classes, functions, etc, we use `numpy <https://github.com/numpy/numpy/blob/master/doc/HOWTO_DOCUMENT.rst.txt>`_ as the canonical reference.
 
 

docs/source/index.rst

@@ -1,12 +1,23 @@
-.. include:: ../../README.rst
+.. include:: welcome.rst
+|
+|
+Table of Contents
+-----------------
 
 .. toctree::
    :maxdepth: 1
 
    install
    beginner-tutorial
-   bundles
+   jupyter
+   live-trading
+   naming-convention
+   videos
+   resources
    development-guidelines
-   appendix
-   release-process
    releases
+..   bundles
+..   development-guidelines
+..   appendix
+..   release-process
+

docs/source/install.rst

@@ -1,40 +1,65 @@
 Install
 =======
 
+To get started with Catalyst, you will need to install it in your computer. 
+Like any other piece of software, Catalyst has a number of dependencies 
+(other software on which it depends to run) that you will need to install, as 
+well. We recommend using a software named ``Conda`` that will manage all 
+these dependencies for you, and set up the environment needed to get you up 
+and running as easily as possible. See :ref:`Installing with Conda <conda>`.
+
 Installing with ``pip``
 -----------------------
 
-Installing Zipline via ``pip`` is slightly more involved than the average
+Installing Catalyst via ``pip`` is slightly more involved than the average
 Python package.
 
 There are two reasons for the additional complexity:
 
-1. Zipline ships several C extensions that require access to the CPython C API.
-   In order to build the C extensions, ``pip`` needs access to the CPython
-   header files for your Python installation.
+1. Catalyst ships several C extensions that require access to the CPython C 
+   API. In order to build the C extensions, ``pip`` needs access to the 
+   CPython header files for your Python installation.
 
-2. Zipline depends on `numpy <http://www.numpy.org/>`_, the core library for
+2. Catalyst depends on `numpy <http://www.numpy.org/>`_, the core library for
    numerical array computing in Python.  Numpy depends on having the `LAPACK
    <http://www.netlib.org/lapack>`_ linear algebra routines available.
 
-Because LAPACK and the CPython headers are non-Python dependencies, the correct
-way to install them varies from platform to platform.  If you'd rather use a
-single tool to install Python and non-Python dependencies, or if you're already
-using `Anaconda <http://continuum.io/downloads>`_ as your Python distribution,
-you can skip to the :ref:`Installing with Conda <conda>` section.
+Because LAPACK and the CPython headers are non-Python dependencies, the 
+correctway to install them varies from platform to platform.  If you'd rather 
+use a single tool to install Python and non-Python dependencies, or if you're 
+already using `Anaconda <http://continuum.io/downloads>`_ as your Python 
+distribution, you can skip to the :ref:`Installing with Conda <conda>` 
+section.
 
 Once you've installed the necessary additional dependencies (see below for
 your particular platform), you should be able to simply run
 
 .. code-block:: bash
 
-   $ pip install zipline
+   $ pip install enigma-catalyst
 
-If you use Python for anything other than Zipline, we **strongly** recommend
+If you use Python for anything other than Catalyst, we **strongly** recommend
 that you install in a `virtualenv
 <https://virtualenv.readthedocs.org/en/latest>`_.  The `Hitchhiker's Guide to
 Python`_ provides an `excellent tutorial on virtualenv
-<http://docs.python-guide.org/en/latest/dev/virtualenvs/>`_.
+<http://docs.python-guide.org/en/latest/dev/virtualenvs/>`_. Here's a 
+summarized version:
+
+.. code-block:: bash
+
+   $ pip install virtualenv
+   $ virtualenv catalyst-venv
+   $ source ./catalyst-venv/bin/activate
+   $ pip install enigma-catalyst
+
+Though not required by Catalyst directly, our example algorithms use 
+matplotlib to visually display the results of the trading algorithms. If you 
+wish to run any examples or use matplotlib during development, it can be 
+installed using:
+
+.. code-block:: bash
+
+    $ pip install matplotlib
 
 GNU/Linux
 ~~~~~~~~~
@@ -60,25 +85,27 @@ On `Arch Linux`_, you can acquire the additional dependencies via ``pacman``:
 
    $ pacman -S lapack gcc gcc-fortran pkg-config
 
-There are also AUR packages available for installing `Python 3.4
-<https://aur.archlinux.org/packages/python34/>`_ (Arch's default python is now
-3.5, but Zipline only currently supports 3.4), and `ta-lib
-<https://aur.archlinux.org/packages/ta-lib/>`_, an optional Zipline dependency.
-Python 2 is also installable via:
+.. Commenting it out until Catalyst fully supports Python 3.X
+..
+.. There are also AUR packages available for installing `Python 3.4
+.. <https://aur.archlinux.org/packages/python34/>`_ (Arch's default python is now
+.. 3.5, but Catalyst only currently supports 3.4), and `ta-lib
+.. <https://aur.archlinux.org/packages/ta-lib/>`_, an optional Catalyst dependency.
+.. Python 2 is also installable via:
 
-.. code-block:: bash
+.. 
 
-   $ pacman -S python2
+..   $ pacman -S python2
 
 OSX
 ~~~
 
-The version of Python shipped with OSX by default is generally out of date, and
-has a number of quirks because it's used directly by the operating system.  For
-these reasons, many developers choose to install and use a separate Python
+The version of Python shipped with OSX by default is generally out of date, 
+and has a number of quirks because it's used directly by the operating system.
+For these reasons, many developers choose to install and use a separate Python
 installation. The `Hitchhiker's Guide to Python`_ provides an excellent guide
-to `Installing Python on OSX <http://docs.python-guide.org/en/latest/>`_, which
-explains how to install Python with the `Homebrew`_ manager.
+to `Installing Python on OSX <http://docs.python-guide.org/en/latest/>`_, 
+which explains how to install Python with the `Homebrew`_ manager.
 
 Assuming you've installed Python with Homebrew, you'll also likely need the
 following brew packages:
@@ -87,36 +114,294 @@ following brew packages:
 
    $ brew install freetype pkg-config gcc openssl
 
+OSX + virtualenv + matplotlib
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+A note about using matplotlib in virtual enviroments on OSX: it may be 
+necessary to run
+
+.. code-block:: bash
+
+   echo "backend: TkAgg" > ~/.matplotlib/matplotlibrc
+
+in order to override the default ``macosx`` backend for your system, which 
+may not be accessible from inside the virtual environment. This will allow 
+Catalyst to open matplotlib charts from within a virtual environment, which 
+is useful for displaying the performance of your backtests.  To learn more 
+about matplotlib backends, please refer to the
+`matplotlib backend documentation <https://matplotlib.org/faq/usage_faq.html#what-is-a-backend>`_.
+
+.. _windows:
+
 Windows
 ~~~~~~~
 
-For windows, the easiest and best supported way to install zipline is to use
+In Windows, you will need the `Microsoft Visual C++ Compiler for Python 2.7 
+<https://www.microsoft.com/en-us/download/details.aspx?id=44266>`_. This 
+package contains the compiler and the set of system headers necessary for 
+producing binary wheels for Python 2.7 packages. If it's not already in your 
+system, download it and install it before proceeding to the next step.
+
+For windows, the easiest and best supported way to install Catalyst is to use
 :ref:`Conda <conda>`.
 
+Some problems we have encountered installing the **Visual C++ Compiler** 
+mentioned above are as follows:
+
+- **The system administrator has set policies to prevent this installation**.
+  
+  In some systems, there is a default *Windows Software Restriction* policy 
+  that prevents the installation of some software packages like this one. 
+  You'll have to change the Registry to circumvent this:
+
+  - Click ``Start``, and search for ``regedit`` and launch the 
+    ``Registry Editor``
+  - Navigate to the following folder:
+    ``HKEY_LOCAL_MACHINE\SOFTWARE\Policies\Microsoft\Windows\Installer``
+  - If there is an entry for ``DisableMSI``, set the Value data to 0.
+  - If there is no such entry, click on the ``Edit`` menu -> ``New`` -> 
+    ``DWORD (32-bit) Value`` and enter ``DisableMSI`` as the Name (and by 
+    default you get 0 as the Value Data)
+
+|
+- **The installer has encountered an unexpected error installing this package. 
+  This may indicate a problem with this package. The error code is 2503.**
+
+  We have observed this when trying to install a package without enough 
+  administrator permissions. Even when you are logged in as an Administrator, 
+  you have to explictily install this package with administrator privileges:
+
+  - Click ``Start`` and find ``CMD`` or ``Command Prompt``
+  - Right click on it and choose ``Run as administrator``
+  - ``cd`` into the folder where you downloaded ``VCForPython27.msi``
+  - Run ``msiexec /i VCForPython27.msi``
+
+
+Amazon Linux AMI
+~~~~~~~~~~~~~~~~
+
+The packages ``pip`` and ``setuptools`` that come shipped by default are very 
+outdated. Thus, you first need to run:
+
+.. code-block:: bash
+
+   pip install --upgrade pip setuptools
+
+The default installation is also missing the C and C++ compilers, which you 
+install by:
+
+.. code-block:: bash
+
+   sudo yum install gcc gcc-c++
+
+Then you should follow the regular installation instructions outlined at the 
+beginning of this page.
+
+
+Troubleshooting ``pip`` Install
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+**Issue**: 
+   Package enigma-catalyst cannot be found 
+ 
+**Solution**: 
+   Make sure you have the most up-to-date version of pip installed, by running: 
+
+   .. code-block:: bash
+
+      pip install --upgrade pip
+
+   On Windows, the recommended command is:
+
+   .. code-block:: bash
+
+      python -m pip install --upgrade pip
+
+----
+
+**Issue**: 
+   Package enigma-catalyst cannot still be found, even after upgrading pip 
+   (see above), with an error similar to:
+
+   .. code-block:: bash
+
+      Downloading/unpacking enigma-catalyst
+      Could not find a version that satisfies the requirement enigma-catalyst 
+      (from versions: 0.1.dev9, 0.2.dev2, 0.1.dev4, 0.1.dev5, 0.1.dev3, 
+      0.2.dev1, 0.1.dev8, 0.1.dev6)
+      Cleaning up...
+      No distributions matching the version for enigma-catalyst
+
+**Solution**:
+   In some systems (this error has been reported in Ubuntu), pip is configured 
+   to only find stable versions by default. Since Catalyst is in alpha 
+   version, pip cannot find a matching version that satisfies the installation 
+   requirements. The solution is to include the `--pre` flag to include 
+   pre-release and development versions:
+
+   .. code-block:: bash
+
+      pip install --pre enigma-catalyst
+
+----
+
+**Issue**: 
+   Package enigma-catalyst fails to install because of outdated setuptools
+
+**Solution**: 
+   Upgrade to the most up-to-date setuptools package by running: 
+
+   .. code-block:: bash
+
+      pip install --upgrade pip setuptools
+
+----
+
+**Issue**:
+   Missing required packages  
+
+**Solution**:
+   Download `requirements.txt 
+   <https://github.com/enigmampc/catalyst/blob/master/etc/requirements.txt>`_ 
+   (click on the *Raw* button and Right click -> Save As...) and use it to
+   install all the required dependencies by running:
+
+   .. code-block:: bash
+
+      pip install -r requirements.txt
+
+----
+
+**Issue**: 
+   Installation fails with error: 
+   ``fatal error: Python.h: No such file or directory``
+
+**Solution**: 
+   Some systems (this issue has been reported in Ubuntu) require `python-dev` 
+   for the proper build and installation of package dependencies. The solution 
+   is to install python-dev, which is independent of the virtual environment. 
+   In Ubuntu, you would need to run:
+
+   .. code-block:: bash
+
+      sudo apt-get install python-dev
+
+
 .. _conda:
 
 Installing with ``conda``
 -------------------------
 
-Another way to install Zipline is via the ``conda`` package manager, which
+Another way to install Catalyst is via the ``conda`` package manager, which
 comes as part of Continuum Analytics' `Anaconda
 <http://continuum.io/downloads>`_ distribution.
 
 The primary advantage of using Conda over ``pip`` is that conda natively
 understands the complex binary dependencies of packages like ``numpy`` and
-``scipy``.  This means that ``conda`` can install Zipline and its dependencies
-without requiring the use of a second tool to acquire Zipline's non-Python
-dependencies.
+``scipy``.  This means that ``conda`` can install Catalyst and its 
+dependencies without requiring the use of a second tool to acquire Catalyst's 
+non-Python dependencies.
+
+  For Windows, you will need the *Microsoft Visual C++ Compiler for Python 
+  2.7*. Follow the instructions on the :ref:`Windows` section and come back 
+  here.
 
 For instructions on how to install ``conda``, see the `Conda Installation
-Documentation <http://conda.pydata.org/docs/download.html>`_
+Documentation <http://conda.pydata.org/docs/download.html>`_. Alternatively, 
+you can install MiniConda, which is a smaller footprint (fewer packages and 
+smaller size) than its big brother Anaconda, but it still contains all the 
+main packages needed. To install MiniConda, you can follow these steps:
 
-Once conda has been set up you can install Zipline from our ``Quantopian``
-channel:
+1. Download `MiniConda <https://conda.io/miniconda.html>`_. Select Python 2.7 
+   for your Operating System.
+2. Install MiniConda. See the `Installation Instructions 
+   <https://conda.io/docs/user-guide/install/index.html>`_ if you need help.
+3. Ensure the correct installation by running ``conda list`` in a Terminal 
+   window, which should print the list of packages installed with Conda.
 
-.. code-block:: bash
+Once either Conda or MiniConda has been set up you can install Catalyst:
+
+1. Download the file `python2.7-environment.yml 
+   <https://github.com/enigmampc/catalyst/blob/master/etc/python2.7-environment.yml>`_.
+2. Open a Terminal window and enter [``cd/dir``] into the directory where you 
+   saved the above ``python2.7-environment.yml`` file.
+3. Install using this file. This step can take about 5-10 minutes to install.
+
+   .. code-block:: bash
+
+      conda env create -f python2.7-environment.yml
+
+4. Activate the environment (which you need to do every time you start a new 
+   session to run Catalyst):
+
+   **Linux or OSX:**
+
+   .. code-block:: bash
+
+      source activate catalyst
+
+   **Windows:**
+
+   .. code-block:: bash
+
+      activate catalyst
+
+Congratulations! You now have Catalyst installed.
+
+Troubleshooting ``conda`` Install
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If the command  ``conda env create -f python2.7-environment.yml`` in step 3 
+above failed for any reason, you can try setting up the environment manually 
+with the following steps:
+
+1. Create the environment:
+
+   .. code-block:: bash
+
+      conda create --name catalyst python=2.7 scipy zlib
+
+2. Activate the environment:
+
+   **Linux or OSX:**
+
+   .. code-block:: bash
+
+      source activate catalyst
+
+   **Windows:**
+
+   .. code-block:: bash
+
+      activate catalyst
+
+3. Install the Catalyst inside the environment:
+
+   .. code-block:: bash
+
+      pip install enigma-catalyst matplotlib
+
+Getting Help
+------------
+
+If after following the instructions above, and going through the 
+*Troubleshooting* sections, you still experience problems installing Catalyst,
+you can seek additional help through the following channels:
+
+- Join our `Discord community <https://discord.gg/SJK32GY>`_, and head over 
+  the #catalyst_dev channel where many other users (as well as the project 
+  developers) hang out, and can assist you with your particular issue. The 
+  more descriptive and the more information you can provide, the easiest will 
+  be for others to help you out.
+
+- Report the problem you are experiencing on our 
+  `GitHub repository <https://github.com/enigmampc/catalyst/issues>`_ 
+  following the guidelines provided therein. Before you do so, take a moment 
+  to browse through all `previous reported issues
+  <https://github.com/enigmampc/catalyst/issues?utf8=%E2%9C%93&q=is%3Aissue>`_ 
+  in the likely case that someone else experienced that same issue before, 
+  and you get a hint on how to solve it.
 
-    conda install -c Quantopian zipline
 
 .. _`Debian-derived`: https://www.debian.org/misc/children-distros
 .. _`RHEL-derived`: https://en.wikipedia.org/wiki/Red_Hat_Enterprise_Linux_derivatives

docs/source/live-trading.rst

@@ -0,0 +1,118 @@
+Live Trading
+============
+This document explains how to get started with live trading.
+
+Supported Exchanges
+^^^^^^^^^^^^^^^^^^^
+Catalyst can trade against these exchanges:
+
+- Bitfinex, id= ``bitfinex``
+- Bittrex, id= ``bittrex``
+- Poloniex, id= ``poloniex``
+
+Authentication
+^^^^^^^^^^^^^^
+Most exchanges require token key/secret combination for authentication. By
+convention, Catalyst uses an ``auth.json`` file to hold this data.
+
+This example illustrates the convention using the *Bitfinex* exchange.
+Here is how to generate key and secret values for the Bitfinex exchange:
+https://docs.bitfinex.com/v1/docs/api-access. Most exchanges follow
+a similar process.
+
+The auth.json file:
+
+.. code-block:: json
+
+  {
+    "name": "bitfinex",
+    "key": "my-key",
+    "secret": "my-secret"
+  }
+
+
+The file goes here: ``~/.catalyst/data/exchanges/bitfinex/auth.json``
+
+Note that the `bitfinex` part in the directory above corresponds to the id of the Bitfinex
+exchange as defined in the "Supported Exchanges" section above.
+Attempting to run an algorithm where the targeted exchange is missing
+its ``auth.json`` file will create the directory structure and create an empty
+auth.json file, but will result in an error.
+
+Currency Symbols
+^^^^^^^^^^^^^^^^
+Catalyst introduces a universal convention to reference
+trading pairs and individual currencies. This
+is required to ensure that the ``symbol()`` api predictably
+returns the correct asset regardless of the targeted exchange.
+
+Exchanges tend to use their own convention to represent currencies
+(e.g. XBT and BTC both represent Bitcoin on different exchanges).
+Trading pairs are also inconsistent. For example, Bitfinex
+puts the market currency before the base currency without a
+separator, Bittrex puts the base currency first and uses a dash
+seperator.
+
+Here is the Catalyst convention:
+
+*[Market Currency]_[Base Currency]* all lowercase.
+
+Currency symbols (e.g. btc, eth, ltc) follow the Bittrex convention.
+
+Here are some examples:
+
+.. code-block:: json
+
+  # With Bitfinex
+  bitcoin_usd_asset = symbol('btc_usd')
+  ethereum_bitcoin_asset = symbol('eth_btc')
+
+  # With Bittrex
+  ethereum_bitcoin_asset = symbol('eth_btc')
+  neo_ethereum_asset = symbol('neo_eth)
+
+Note that the trading pairs are always referenced in the same manner.
+However, not all trading pairs are available on all exchanges. An
+error will occur if the specified trading pair is not trading
+on the exchange. To check which currency pairs are available on each 
+of the supported exchanges, see `Catalyst Market Coverage <https://www.enigma.co/catalyst/status`_.
+
+Trading an Algorithm
+^^^^^^^^^^^^^^^^^^^^
+There is no special convention to follow when writing an
+algorithm for live trading. The same algorithm should work in
+backtest and live execution mode without modification.
+
+What differs are the arguments provided to the catalyst client or
+`run_algorithm()` interface. Here is the same example in both interfaces:
+
+.. code-block:: bash
+
+  catalyst live -f my_algo_code -x bitfinex -c btc -n my_algo_name 
+
+.. code-block:: python
+
+  run_algorithm(
+      initialize=initialize,
+      handle_data=handle_data,
+      analyze=analyze,
+      exchange_name='bitfinex',
+      live=True,
+      algo_namespace='my_algo_name',
+      base_currency='btc'
+  )
+
+
+Here is the breakdown of the new arguments:
+
+- ``live``: Boolean flag which enables live trading.
+- ``exchange_name``: The name of the targeted exchange
+  (supported values: *bitfinex*, *bittrex*).
+- ``algo_namespace``: A arbitrary label assigned to your algorithm for
+  data storage purposes.
+- ``base_currency``: The base currency used to calculate the
+  statistics of your algorithm. Currently, the base currency of all
+  trading pairs of your algorithm must match this value.
+
+Here is a complete algorithm for reference:
+`Buy Low and Sell High <https://github.com/enigmampc/catalyst/blob/master/catalyst/examples/buy_low_sell_high_live.py>`_

docs/source/naming-convention.rst

@@ -0,0 +1,66 @@
+Naming Convention
+=================
+
+Catalyst introduces a standardized naming convention for all asset pairs 
+trading on any exchange in the following form:
+
+
+    **{market_currency}_{base_currency}**
+
+Where {market_currency} is the asset to be traded using {base_currency} as 
+the reference, both written in lowercase and separated with an underscore.
+
+This standardization is needed to overcome the lack of consistency in the 
+naming of assets across different exchanges, and making it easier to the user
+to refer to the asset pairs that you want to trade.
+
+Catalyst maintains a `Market Coverage Overview <https://www.enigma.co/catalyst/status>`_ 
+where you can check the mapping between Catalyst naming pairs and that of each 
+exchange. Catalyst will always expect in all its functions that you will refer to 
+the asset pairs by using the Catalyst naming convention.
+
+If at any point, you input the wrong name for an asset pair, you will get an error 
+of that pair not found in the given exchange, and a list of pairs available on that exchange:
+
+.. code-block:: bash
+
+   $ catalyst ingest-exchange -x poloniex -i btc_usd
+
+.. parsed-literal::
+
+	Ingesting exchange bundle poloniex...
+	Error traceback: /Volumes/Data/Users/victoris/Desktop/Enigma/user-install/catalyst-dev/catalyst/exchange/exchange.py (line 175)
+	SymbolNotFoundOnExchange:  Symbol btc_usd not found on exchange Poloniex. 
+	Choose from: ['rep_usdt', 'gno_btc', 'xvc_btc', 'pink_btc', 'sys_btc', 
+	'emc2_btc', 'rads_btc', 'note_btc', 'maid_btc', 'bch_btc', 'gnt_btc', 
+	'bcn_btc', 'rep_btc', 'bcy_btc', 'cvc_btc', 'nxt_xmr', 'zec_usdt', 
+	'fct_btc', 'gas_btc', 'pot_btc', 'eth_usdt', 'btc_usdt', 'lbc_btc', 
+	'dcr_btc', 'etc_usdt', 'omg_eth', 'amp_btc', 'xpm_btc', 'nxt_btc', 
+	'vtc_btc', 'steem_eth', 'blk_xmr', 'pasc_btc', 'zec_xmr', 'grc_btc', 
+	'nxc_btc', 'btcd_btc', 'ltc_btc', 'dash_btc', 'naut_btc', 'zec_eth', 
+	'zec_btc', 'burst_btc', 'zrx_eth', 'bela_btc', 'steem_btc', 'etc_btc', 
+	'eth_btc', 'huc_btc', 'strat_btc', 'lsk_btc', 'exp_btc', 'clam_btc', 
+	'rep_eth', 'dash_xmr', 'cvc_eth', 'bch_usdt', 'zrx_btc', 'dash_usdt', 
+	'blk_btc', 'xrp_btc', 'nxt_usdt', 'neos_btc', 'omg_btc', 'bts_btc', 
+	'doge_btc', 'gnt_eth', 'sbd_btc', 'gno_eth', 'xcp_btc', 'ltc_usdt', 
+	'btm_btc', 'xmr_usdt', 'lsk_eth', 'omni_btc', 'nav_btc', 'fldc_btc', 
+	'ppc_btc', 'xbc_btc', 'dgb_btc', 'sc_btc', 'btcd_xmr', 'vrc_btc', 
+	'ric_btc', 'str_btc', 'maid_xmr', 'xmr_btc', 'sjcx_btc', 'via_btc', 
+	'xem_btc', 'nmc_btc', 'etc_eth', 'ltc_xmr', 'ardr_btc', 'gas_eth', 
+	'flo_btc', 'xrp_usdt', 'game_btc', 'bch_eth', 'bcn_xmr', 'str_usdt']
+
+In the example above, exchange Poloniex does not use USD, but uses instead the 
+USDT cryptocurrency asset that is issued on the Bitcoin blockchain via the Omni
+Layer Protocol. Each USDT unit is backed by a U.S Dollar held in the reserves of 
+Tether Limited. USDT can be transferred, stored, and spent, just like bitcoins 
+or any other cryptocurrency. Given its 1:1 mapping to the USD, is a viable alternative.
+
+.. code-block:: bash
+
+   $ catalyst ingest-exchange -x poloniex -i btc_usdt
+
+.. parsed-literal::
+
+	Ingesting exchange bundle poloniex...
+	    [====================================]  Fetching poloniex daily candles: :  100%
+

docs/source/releases.rst

@@ -2,24 +2,194 @@
 Release Notes
 =============
 
-.. include:: whatsnew/1.1.1.txt
+Version 0.3.6
+^^^^^^^^^^^^^
+**Release Date**: 2017-11-4
 
-.. include:: whatsnew/1.1.0.txt
+Bug Fixes
+~~~~~~~~~
 
-.. include:: whatsnew/1.0.2.txt
+- Fixed an issue with single bar data.history() (:issue:`55`)
 
-.. include:: whatsnew/1.0.1.txt
+Version 0.3.5
+^^^^^^^^^^^^^
+**Release Date**: 2017-11-4
 
-.. include:: whatsnew/1.0.0.txt
+Bug Fixes
+~~~~~~~~~
 
-.. include:: whatsnew/0.9.0.txt
+- Added workaround for: KeyError: Timestamp error (:issue:`53`)
 
-.. include:: whatsnew/0.8.4.txt
+Version 0.3.4
+^^^^^^^^^^^^^
+**Release Date**: 2017-11-2
 
-.. include:: whatsnew/0.8.3.txt
+Bug Fixes
+~~~~~~~~~
 
-.. include:: whatsnew/0.8.0.txt
+- Fixed issue with auto-ingestion of minute data (:issue:`47`)
+- Fixed issue with sell orders in backtesting
+- Fixed data frequency issues with data.history() in backtesting
+- Fixed an issue with can_trade()
+- Reduced the commission and slippage values to account for lower volume transactions
 
-.. include:: whatsnew/0.7.0.txt
+Build
+~~~~~
+
+- Added more unit tests
+
+Documentation
+~~~~~~~~~~~~~
+
+- Improved installation notes for Windows C++ compiler and Conda
+- Addition of `Jupyter Notebook guide <https://enigmampc.github.io/catalyst/jupyter.html>`_
+- Addition of `Live Trading page <https://enigmampc.github.io/catalyst/live-trading.html>`_
+- Addition of `Videos page <https://enigmampc.github.io/catalyst/videos.html>`_
+- Addition of `Resources page <https://enigmampc.github.io/catalyst/resources.html>`_
+- Addition of `Development Guidelines <https://enigmampc.github.io/catalyst/development-guidelines.html>`_
+- Addition of `Release Notes <https://enigmampc.github.io/catalyst/releases.html>`_
+- Updated code docstrings
+
+
+Version 0.3.3
+^^^^^^^^^^^^^
+**Release Date**: 2017-10-26
+
+Bug Fixes
+~~~~~~~~~
+
+- Fix missing -x in ingest-exchange
+- Fix issue with daily chunks end date (data bundles)
+- Fix issue in the prepare_chunk logic (data bundles)
+
+Build
+~~~~~
+
+- Added data validation unit tests
+
+
+Version 0.3.2
+^^^^^^^^^^^^^
+**Release Date**: 2017-10-25
+
+Bug Fixes
+~~~~~~~~~
+
+- Fix to work with empty data bundles
+- Fix Windows path of ``$HOME/.catalyst`` folder
+- Fix ``etc/python2.7-environment.yml`` for Windows Conda install
+- Fix hash method to create sid numbers compatible across platforms
+- Fix an issue with asset date in chunks
+
+Build
+~~~~~
+
+- Python3 adjustments
+- Added method to clean bundle folders, and remove symbols.json
+- Implemented and improved unit tests
+
+
+Version 0.3.1
+^^^^^^^^^^^^^
+**Release Date**: 2017-10-22
+
+Bug Fixes
+~~~~~~~~~
+
+- Fixed OS-dependent path issue in data bundle
+- Changed handling of empty ``auth.json``, instead of throwing an error for missing file
+- Updated ``etc/python2.7-environment.yml`` to work with Catalyst version 0.3
+- Updated ``catalyst/examples/buy_and_hodl.py``  and ``catalyst/examples/buy_low_sell_high.py`` to work with Catalyst version 0.3
+
+
+Version 0.3
+^^^^^^^^^^^
+**Release Date**: 2017-10-20
+
+- Standardized live and backtesting syntax
+- Added a repository for historical data
+- Added supported for multiple exchanges per algorithm
+- Added a standardized dictionary of symbols for each exchange
+- Added auto-ingestion of bundle data while backtesting
+- Bug fixes
+
+
+Version 0.2.dev5
+^^^^^^^^^^^^^^^^
+**Release Date**: 2017-10-03
+
+- Fixes bug in data.history function that was formatting 'volume' data as integers, now they are returned as floats with up to 9 decimals of precision. Data bundles redone.
+
+Version 0.2.dev4 
+^^^^^^^^^^^^^^^^
+
+**Release Date**: 2017-09-20
+
+- Fixes bug in the pricing resolution of 1-minute data, now set to 8 decimal places. Pricing resolution of daily data remains set to 9 decimal places.
+- The current data bundle takes 340MB compressed for download, and 460MB uncompressed on disk for Catalyst to use.
+
+Version 0.2.dev3
+^^^^^^^^^^^^^^^^
+
+**Release Date**: 2017-09-20
+
+- 1-minute resolution OHLCV data bundle for backtesting from Poloniex exchange
+- Implementation of trading of fractional crypto assets (i.e. 0.01 BTC)
+- Minimum trade size of a coin can be configured on a per-coin basis, defaults to 0.00000001 in backtesting (most exchanges set the minimum trade to larger amounts, which will impact live trading)
+- Increased pricing resolution from 3 to 9 decimal places
+- The current data bundle takes 40MB compressed for download, and 99MB uncompressed on disk for Catalyst to use.
+
+Version 0.2.dev2 
+^^^^^^^^^^^^^^^^
+
+**Release Date**: 2017-09-07
+
+- Fix path issue
+
+Version 0.2.dev1
+^^^^^^^^^^^^^^^^
+
+**Release Date**: 2017-09-03
+
+- Implementation of live trading:
+
+  - Comprehensive trading functionality against exchanges Bitfinex and Bittrex.
+  - Support for all trading pairs available on each exchange.
+  - Multiple algorithms can trade simultaneously against a single exchange using the same account.
+  - Each algorithm has a persisted state (i.e. algorithm can be stopped and restarted preserving the state without data loss) that tracks all open orders, executed transactions and portfolio positions.
+
+- Minute by minute portfolio performance metrics.
+
+  - Daily summary performance statistics compatible with pyfolio, a Python library for performance and risk analysis of financial portfolios
+
+Version 0.1.dev9
+^^^^^^^^^^^^^^^^
+
+**Release Date**: 2017-08-28
+
+- Retrieval of crypto benchmark from bundle, instead of hitting Poloniex exchange directly
+- Change of bundle storage provider from Dropbox to AWS
+- Fix issue with 1/1000 scaling issue of prices in bundle
+
+Version 0.1.dev8
+^^^^^^^^^^^^^^^^ 
+
+**Release Date**: 2017-08-18
+
+- Fixes issue in the creation of bundles (:issue:`27`)
+
+
+Version 0.1.dev7
+^^^^^^^^^^^^^^^^
+- Fixes issues in empty benchmark (:issue:`16`)
+- Fixes issue of normalizing timestamps before comparison (:issue:`24`)
+- Generic data bundles
+- CLI UI improvements
+
+Version 0.1.dev6
+^^^^^^^^^^^^^^^^
+
+**Release Date**: 2017-07-13
+
+- Initial public release
 
-.. include:: whatsnew/0.6.1.txt

docs/source/resources.rst

@@ -0,0 +1,26 @@
+Resources
+=========
+
+-  `Catalyst Whitepaper <https://www.enigma.co/enigma_catalyst.pdf>`_ 
+
+
+Related 3rd Party APIs
+^^^^^^^^^^^^^^^^^^^^^^
+
+- `Zipline <http://www.zipline.io/appendix.html>`_ is a Pythonic Algorithmic 
+  Trading Library, and the project Catalyst forked off in the spring of 2017.
+- `Quantopian <https://www.quantopian.com/help>`_ provides a platform for 
+  freelance quantitative analysts develop, test, and use trading algorithms to 
+  buy and sell securities. They aim to create a crowd-sourced hedge fund by
+  fostering their community of freelance traders. Quantopian's backtesting and 
+  live-trading engine is powered by *Zipline*.
+- `Pandas <https://pandas.pydata.org/pandas-docs/stable/api.html>`_ is a Python
+  library providing high-performance, easy-to-use data structures and data 
+  analysis tools. Catalyst relies heavily on pandas, and many API functions 
+  return data as Pandas dataframes.
+- `Numpy <https://docs.scipy.org/doc/numpy/reference/>`_ is the fundamental 
+  package for scientific computing with Python. Some of the data computation 
+  that your algorithms will need, will be optimized leveraging Numpy.
+- `Matplotlib <https://matplotlib.org/1.5.3/api/index.html>`_ is a Python 2D 
+  plotting library that many of examples rely on to plot the performance of 
+  trading algorithms

docs/source/videos.rst

@@ -0,0 +1,26 @@
+Videos
+======
+
+
+Installation: MacOS
+-------------------
+
+.. raw:: html
+
+   <iframe width="560" height="315" src="https://www.youtube.com/embed/ZnsslmHljvw" frameborder="0" allowfullscreen></iframe>
+
+|
+|
+Installation: Windows
+---------------------
+
+Where things go smoothly:
+
+.. raw:: html
+
+   <iframe width="560" height="315" src="https://www.youtube.com/embed/H8HqcEbZmkk" frameborder="0" allowfullscreen></iframe>
+
+|
+Where things don't:
+   
+   Coming up next!

docs/source/welcome.rst

@@ -0,0 +1,43 @@
+.. image:: https://s3.amazonaws.com/enigmaco-docs/enigma-catalyst.jpg
+|
+Catalyst is an algorithmic trading library for crypto-assets written in Python.
+It allows trading strategies to be easily expressed and backtested against 
+historical data (with daily and minute resolution), providing analytics and 
+insights regarding a particular strategy's performance. Catalyst also supports
+live-trading of crypto-assets starting with three exchanges (Bitfinex, Bittrex, 
+and Poloniex) with more being added over time. Catalyst empowers users to share 
+and curate data and build profitable, data-driven investment strategies. Please 
+visit `enigma.co <https://www.enigma.co>`_ to learn more about Catalyst, or 
+refer to the `whitepaper <https://www.enigma.co/enigma_catalyst.pdf>`_ for 
+further technical details.
+
+Catalyst builds on top of the well-established 
+`Zipline <https://github.com/quantopian/zipline>`_ project. We did our best to 
+minimize structural changes to the general API to maximize compatibility with 
+existing trading algorithms, developer knowledge, and tutorials. Join us on 
+`Discord <https://discord.gg/SJK32GY>`_ where we have a *#catalyst_dev* channel 
+for questions around Catalyst, algorithmic trading and technical support.
+
+Features
+========
+
+-  Ease of use: Catalyst tries to get out of your way so that you can 
+   focus on algorithm development. See 
+   `examples of trading strategies <https://github.com/enigmampc/catalyst/tree/master/catalyst/examples>`_ 
+   provided.
+-  Support for several of the top crypto-exchanges by trading volume:
+   `Bitfinex <https://www.bitfinex.com>`_, `Bittrex <http://www.bittrex.com>`_,
+   and `Poloniex <https://www.poloniex.com>`_. 
+-  Secure: You and only you have access to each exchange API keys for your accounts.
+-  Input of historical pricing data of all crypto-assets by exchange, 
+   with daily and minute resolution. See 
+   `Catalyst Market Coverage Overview <https://www.enigma.co/catalyst/status>`_.
+-  Backtesting and live-trading functionality, with a seamless transition
+   between the two modes.
+-  Output of performance statistics are based on Pandas DataFrames to 
+   integrate nicely into the existing PyData eco-system.
+-  Statistic and machine learning libraries like matplotlib, scipy, 
+   statsmodels, and sklearn support development, analysis, and 
+   visualization of state-of-the-art trading systems.
+-  Addition of Bitcoin price (btc_usdt) as a benchmark for comparing 
+   performance across trading algorithms.

etc/python2.7-environment.yml

@@ -1,30 +1,22 @@
 name: catalyst
 channels:
-- statiskit
 - defaults
 dependencies:
 - certifi=2016.2.28=py27_0
-- coverage=4.4.1=py27_0
-- nose=1.3.7=py27_1
-- openssl=1.0.2l=0
-- path.py=10.3.1=py27_0
+- mkl=2017.0.3
+- numpy=1.13.1=py27_0
+- openssl=1.0.2l
 - pip=9.0.1=py27_1
-- python=2.7.13=0
-- pyyaml=3.12=py27_0
-- readline=6.2=2
-- setuptools=36.4.0=py27_0
-- six=1.10.0=py27_0
-- sqlite=3.13.0=0
-- tk=8.5.18=0
+- python=2.7.13
+- scipy=0.19.1=np113py27_0
+- setuptools=36.4.0=py27_1
+- sqlite=3.13.0
+- tk=8.5.18
 - wheel=0.29.0=py27_0
-- yaml=0.1.6=0
-- zlib=1.2.11=0
-- libdev=1.0.0=py27_0
-- python-dev=1.0.0=py27_0
-- python-scons=3.0.0=py27_0
+- zlib=1.2.11
 - pip:
-  - alembic==0.9.5
-  - backports.shutil-get-terminal-size==1.0.0
+  - alembic==0.9.6
+  - backports.functools-lru-cache==1.4
   - bcolz==0.12.1
   - bottleneck==1.2.1
   - chardet==3.0.4
@@ -32,36 +24,22 @@ dependencies:
   - contextlib2==0.5.5
   - cycler==0.10.0
   - cyordereddict==1.0.0
-  - cython==0.26.1
+  - cython==0.27.1
   - decorator==4.1.2
   - empyrical==0.2.1
-  - enigma-catalyst>=0.2.dev2
-  - enum34==1.1.6
-  - functools32==3.2.3.post2
   - idna==2.6
   - intervaltree==2.1.0
-  - ipdb==0.10.3
-  - ipdbplugin==1.4.5
-  - ipython==5.5.0
-  - ipython-genutils==0.2.0
   - logbook==1.1.0
   - lru-dict==1.1.6
   - mako==1.0.7
   - markupsafe==1.0
-  - matplotlib==2.0.2
+  - matplotlib==2.1.0
   - multipledispatch==0.4.9
-  - networkx==1.11
+  - networkx==2.0
   - numexpr==2.6.4
-  - numpy==1.13.1
   - pandas==0.19.2
   - pandas-datareader==0.5.0
-  - pathlib2==2.3.0
   - patsy==0.4.1
-  - pexpect==4.2.1
-  - pickleshare==0.7.4
-  - prompt-toolkit==1.0.15
-  - ptyprocess==0.5.2
-  - pygments==2.2.0
   - pyparsing==2.2.0
   - python-dateutil==2.6.1
   - python-editor==1.0.3
@@ -69,16 +47,12 @@ dependencies:
   - requests==2.18.4
   - requests-file==1.4.2
   - requests-ftp==0.3.1
-  - scandir==1.5
-  - scipy==0.19.1
-  - scons==3.0.0a20170821
-  - simplegeneric==0.8.1
+  - six==1.11.0
   - sortedcontainers==1.5.7
   - sqlalchemy==1.1.14
   - statsmodels==0.8.0
   - subprocess32==3.2.7
   - tables==3.4.2
   - toolz==0.8.2
-  - traitlets==4.3.2
   - urllib3==1.22
-  - wcwidth==0.1.7
+  - enigma-catalyst>=0.3

etc/requirements.txt

@@ -1,7 +1,7 @@
 # Incompatible with earlier PIP versions
 pip>=7.1.0
 # bcolz fails to install if this is not in the build_requires.
-setuptools>18.0
+setuptools>36.0
 
 # Logging
 Logbook==0.12.5

setup.py

@@ -304,7 +304,7 @@ setup(
                   if '__pycache__' not in root},
     license='Apache 2.0',
     classifiers=[
-        'Development Status :: 2 - Pre-Alpha',
+        'Development Status :: 3 - Alpha',
         'License :: OSI Approved :: Apache Software License',
         'Natural Language :: English',
         'Programming Language :: Python',

tests/exchange/base.py

@@ -1,8 +1,7 @@
-import unittest
 from abc import ABCMeta, abstractmethod
 
 
-class BaseExchangeTestCase():
+class BaseExchangeTestCase:
     __metaclass__ = ABCMeta
 
     @abstractmethod

tests/exchange/test_bcolz.py

@@ -0,0 +1,150 @@
+import shutil
+import random
+import tempfile
+import pandas as pd
+
+from catalyst.exchange.exchange_bundle import ExchangeBundle
+from catalyst.exchange.exchange_bcolz import BcolzExchangeBarWriter, \
+    BcolzExchangeBarReader
+
+from catalyst.exchange.bundle_utils import get_df_from_arrays
+
+from nose.tools import assert_equals
+
+
+class TestBcolzWriter(object):
+    @classmethod
+    def setup_class(cls):
+        cls.columns = ['open', 'high', 'low', 'close', 'volume']
+
+    def setUp(self):
+        self.root_dir = tempfile.mkdtemp()  # Create a temporary directory
+
+    def tearDown(self):
+        shutil.rmtree(self.root_dir)  # Remove the directory after the test
+
+    def generate_df(self, exchange_name, freq, start, end):
+        bundle = ExchangeBundle(exchange_name)
+        index = bundle.get_calendar_periods_range(start, end, freq)
+        df = pd.DataFrame(index=index, columns=self.columns)
+        df.fillna(random.random(), inplace=True)
+        return df
+
+    def test_bcolz_write_daily_past(self):
+        start = pd.to_datetime('2016-01-01')
+        end = pd.to_datetime('2016-12-31')
+        freq = 'daily'
+
+        df = self.generate_df('bitfinex', freq, start, end)
+
+        writer = BcolzExchangeBarWriter(
+            rootdir=self.root_dir,
+            start_session=start,
+            end_session=end,
+            data_frequency=freq,
+            write_metadata=True)
+
+        data = []
+        data.append((1, df))
+        writer.write(data)
+        pass
+
+    def test_bcolz_write_daily_present(self):
+        start = pd.to_datetime('2017-01-01')
+        end = pd.to_datetime('today')
+        freq = 'daily'
+
+        df = self.generate_df('bitfinex', freq, start, end)
+
+        writer = BcolzExchangeBarWriter(
+            rootdir=self.root_dir,
+            start_session=start,
+            end_session=end,
+            data_frequency=freq,
+            write_metadata=True)
+
+        data = []
+        data.append((1, df))
+        writer.write(data)
+        pass
+
+    def test_bcolz_write_minute_past(self):
+        start = pd.to_datetime('2015-04-01 00:00')
+        end = pd.to_datetime('2015-04-30 23:59')
+        freq = 'minute'
+
+        df = self.generate_df('bitfinex', freq, start, end)
+
+        writer = BcolzExchangeBarWriter(
+            rootdir=self.root_dir,
+            start_session=start,
+            end_session=end,
+            data_frequency=freq,
+            write_metadata=True)
+
+        data = []
+        data.append((1, df))
+        writer.write(data)
+
+        pass
+
+    def test_bcolz_write_minute_present(self):
+        start = pd.to_datetime('2017-10-01 00:00')
+        end = pd.to_datetime('today')
+        freq = 'minute'
+
+        df = self.generate_df('bitfinex', freq, start, end)
+
+        writer = BcolzExchangeBarWriter(
+            rootdir=self.root_dir,
+            start_session=start,
+            end_session=end,
+            data_frequency=freq,
+            write_metadata=True)
+
+        data = []
+        data.append((1, df))
+        writer.write(data)
+        pass
+
+    def bcolz_exchange_daily_write_read(self, exchange_name):
+        start = pd.to_datetime('2017-10-01 00:00')
+        end = pd.to_datetime('today')
+        freq = 'daily'
+
+        bundle = ExchangeBundle(exchange_name)
+
+        df = self.generate_df(exchange_name, freq, start, end)
+
+        print df.index[0],df.index[-1]
+
+        writer = BcolzExchangeBarWriter(
+            rootdir=self.root_dir,
+            start_session=df.index[0],
+            end_session=df.index[-1],
+            data_frequency=freq,
+            write_metadata=True)
+
+        data = []
+        data.append((1, df))
+        writer.write(data)
+
+        reader = BcolzExchangeBarReader(rootdir=self.root_dir,
+                                        data_frequency=freq)
+
+        arrays = reader.load_raw_arrays(self.columns, start, end, [1, ])
+
+        periods = bundle.get_calendar_periods_range(
+            start, end, freq
+        )
+
+        dx = get_df_from_arrays(arrays, periods)
+
+        assert_equals(df.equals(df), True)
+        pass
+
+    def test_bcolz_bitfinex_daily_write_read(self):
+        self.bcolz_exchange_daily_write_read('bitfinex')
+
+    def test_bcolz_poloniex_daily_write_read(self):
+        self.bcolz_exchange_daily_write_read('poloniex')

tests/exchange/test_bitfinex.py

@@ -1,20 +1,17 @@
-from catalyst.exchange.bitfinex.bitfinex import Bitfinex
-from .base import BaseExchangeTestCase
 from logbook import Logger
-import pandas as pd
-from catalyst.finance.execution import (MarketOrder,
-                                        LimitOrder,
-                                        StopOrder,
-                                        StopLimitOrder)
+
+from base import BaseExchangeTestCase
+from catalyst.exchange.bitfinex.bitfinex import Bitfinex
 from catalyst.exchange.exchange_utils import get_exchange_auth
+from catalyst.finance.execution import (LimitOrder)
 
 log = Logger('test_bitfinex')
 
 
-class BitfinexTestCase(BaseExchangeTestCase):
+class TestBitfinex(BaseExchangeTestCase):
     @classmethod
     def setup(self):
-        print ('creating bitfinex object')
+        log.info('creating bitfinex object')
         auth = get_exchange_auth('bitfinex')
         self.exchange = Bitfinex(
             key=auth['key'],
@@ -50,13 +47,17 @@ class BitfinexTestCase(BaseExchangeTestCase):
 
     def test_get_candles(self):
         log.info('retrieving candles')
+        ohlcv_neo = self.exchange.get_candles(
+            freq='1T',
+            assets=self.exchange.get_asset('neo_btc')
+        )
         pass
 
     def test_tickers(self):
         log.info('retrieving tickers')
         tickers = self.exchange.tickers([
-            self.exchange.get_asset('eth_usd'),
-            self.exchange.get_asset('btc_usd')
+            self.exchange.get_asset('eth_btc'),
+            self.exchange.get_asset('etc_btc')
         ])
         pass
 
@@ -68,3 +69,9 @@ class BitfinexTestCase(BaseExchangeTestCase):
         log.info('testing exchange balances')
         balances = self.exchange.get_balances()
         pass
+
+    def test_orderbook(self):
+        log.info('testing order book for bitfinex')
+        asset = self.exchange.get_asset('eth_btc')
+        orderbook = self.exchange.get_orderbook(asset)
+        pass

tests/exchange/test_bittrex.py

@@ -1,21 +1,22 @@
+import pandas as pd
 from catalyst.exchange.bittrex.bittrex import Bittrex
 from catalyst.finance.order import Order
-from .base import BaseExchangeTestCase
+from base import BaseExchangeTestCase
 from logbook import Logger
 from catalyst.exchange.exchange_utils import get_exchange_auth
 
 log = Logger('test_bittrex')
 
 
-class BittrexTestCase(BaseExchangeTestCase):
+class TestBittrex(BaseExchangeTestCase):
     @classmethod
     def setup(self):
-        print ('creating bittrex object')
         auth = get_exchange_auth('bittrex')
         self.exchange = Bittrex(
             key=auth['key'],
             secret=auth['secret'],
-            base_currency='btc'
+            base_currency=None,
+            portfolio=None
         )
 
     def test_order(self):
@@ -51,24 +52,27 @@ class BittrexTestCase(BaseExchangeTestCase):
     def test_get_candles(self):
         log.info('retrieving candles')
         ohlcv_neo = self.exchange.get_candles(
-            data_frequency='5m',
-            assets=self.exchange.get_asset('neo_btc')
+            freq='5T',
+            assets=self.exchange.get_asset('neo_btc'),
+            bar_count=20,
+            end_dt=pd.to_datetime('2017-10-20', utc=True)
         )
         ohlcv_neo_ubq = self.exchange.get_candles(
-            data_frequency='5m',
+            freq='1D',
             assets=[
                 self.exchange.get_asset('neo_btc'),
                 self.exchange.get_asset('ubq_btc')
             ],
-            bar_count=14
+            bar_count=14,
+            end_dt=pd.to_datetime('2017-10-20', utc=True)
         )
         pass
 
     def test_tickers(self):
         log.info('retrieving tickers')
         tickers = self.exchange.tickers([
-            self.exchange.get_asset('ubq_btc'),
-            self.exchange.get_asset('neo_btc')
+            self.exchange.get_asset('eth_btc'),
+            self.exchange.get_asset('etc_btc')
         ])
         assert len(tickers) == 2
         pass
@@ -81,3 +85,9 @@ class BittrexTestCase(BaseExchangeTestCase):
     def test_get_account(self):
         log.info('testing account data')
         pass
+
+    def test_orderbook(self):
+        log.info('testing order book for bittrex')
+        asset = self.exchange.get_asset('eth_btc')
+        orderbook = self.exchange.get_orderbook(asset)
+        pass